drupal-mcp-connector 2.7.2 → 2.7.4

package/.claude/commands/drupal-audit-config-best-practices.md

@@ -11,6 +11,6 @@ Lint key configuration for production-readiness and security: on-screen error di
 Parse the request in `$ARGUMENTS` into this tool's parameters:
 
 **Optional:**
-- `site` (string): omit for the default site
+- `site` (string): Named site from connector config. Omit only on reads: multi-site configs fall back to defaultSite (often local/dev, not production). Writes require an explicit site when more than one site is configured. Every response includes `_target` { name, baseUrl, source } (`hint` when you passed site, `default` when you did not).
 
 If a required parameter is missing from `$ARGUMENTS`, ask before calling — do not invent values. Coerce each value to its JSON type (booleans → true/false, numbers → numeric, object/array → parse JSON), then make the single tool call and summarize the result.

package/.claude/commands/drupal-audit-site-health.md

@@ -11,7 +11,7 @@ Composite site-health dashboard: runs a battery of content, link, and configurat
 Parse the request in `$ARGUMENTS` into this tool's parameters:
 
 **Optional:**
-- `site` (string): omit for the default site
+- `site` (string): Named site from connector config. Omit only on reads: multi-site configs fall back to defaultSite (often local/dev, not production). Writes require an explicit site when more than one site is configured. Every response includes `_target` { name, baseUrl, source } (`hint` when you passed site, `default` when you did not).
 - `type` (string): Primary content type for content/link sections (default: article)
 - `sampleSize` (number): Per-section scan cap (kept small for a fast roll-up)
 - `sections` (array (pass as JSON)): Subset of sections to run (default: all). Available: content_summary, stale_content, seo_audit, accessibility, duplicate_content, readability, pii_exposure, broken_links, redirect_health, alias_coverage, log_404, config_best_practices, module_audit, permission_audit

package/.claude/commands/drupal-block-user.md

@@ -14,7 +14,7 @@ Parse the request in `$ARGUMENTS` into this tool's parameters:
 - `id` (string): User UUID
 
 **Optional:**
-- `site` (string): omit for the default site
+- `site` (string): Named site from connector config. Omit only on reads: multi-site configs fall back to defaultSite (often local/dev, not production). Writes require an explicit site when more than one site is configured. Every response includes `_target` { name, baseUrl, source } (`hint` when you passed site, `default` when you did not).
 - `block` (boolean (true/false)): true = block, false = unblock
 
 If a required parameter is missing from `$ARGUMENTS`, ask before calling — do not invent values. Coerce each value to its JSON type (booleans → true/false, numbers → numeric, object/array → parse JSON), then make the single tool call and summarize the result.

package/.claude/commands/drupal-bulk-create.md

@@ -16,6 +16,6 @@ Parse the request in `$ARGUMENTS` into this tool's parameters:
 - `items` (array (pass as JSON)): Entities to create. Each is { attributes?, relationships? }.
 
 **Optional:**
-- `site` (string): omit for the default site
+- `site` (string): Named site from connector config. Omit only on reads: multi-site configs fall back to defaultSite (often local/dev, not production). Writes require an explicit site when more than one site is configured. Every response includes `_target` { name, baseUrl, source } (`hint` when you passed site, `default` when you did not).
 
 If a required parameter is missing from `$ARGUMENTS`, ask before calling — do not invent values. Coerce each value to its JSON type (booleans → true/false, numbers → numeric, object/array → parse JSON), then make the single tool call and summarize the result.

package/.claude/commands/drupal-bulk-update.md

@@ -16,6 +16,6 @@ Parse the request in `$ARGUMENTS` into this tool's parameters:
 - `items` (array (pass as JSON)): Entities to update. Each is { id, attributes?, relationships? }.
 
 **Optional:**
-- `site` (string): omit for the default site
+- `site` (string): Named site from connector config. Omit only on reads: multi-site configs fall back to defaultSite (often local/dev, not production). Writes require an explicit site when more than one site is configured. Every response includes `_target` { name, baseUrl, source } (`hint` when you passed site, `default` when you did not).
 
 If a required parameter is missing from `$ARGUMENTS`, ask before calling — do not invent values. Coerce each value to its JSON type (booleans → true/false, numbers → numeric, object/array → parse JSON), then make the single tool call and summarize the result.

package/.claude/commands/drupal-config-get.md

@@ -14,6 +14,6 @@ Parse the request in `$ARGUMENTS` into this tool's parameters:
 - `name` (string)
 
 **Optional:**
-- `site` (string): omit for the default site
+- `site` (string): Named site from connector config. Omit only on reads: multi-site configs fall back to defaultSite (often local/dev, not production). Writes require an explicit site when more than one site is configured. Every response includes `_target` { name, baseUrl, source } (`hint` when you passed site, `default` when you did not).
 
 If a required parameter is missing from `$ARGUMENTS`, ask before calling — do not invent values. Coerce each value to its JSON type (booleans → true/false, numbers → numeric, object/array → parse JSON), then make the single tool call and summarize the result.

package/.claude/commands/drupal-config-list.md

@@ -11,7 +11,7 @@ List Drupal configuration object names, optionally filtered by a name prefix, vi
 Parse the request in `$ARGUMENTS` into this tool's parameters:
 
 **Optional:**
-- `site` (string): omit for the default site
+- `site` (string): Named site from connector config. Omit only on reads: multi-site configs fall back to defaultSite (often local/dev, not production). Writes require an explicit site when more than one site is configured. Every response includes `_target` { name, baseUrl, source } (`hint` when you passed site, `default` when you did not).
 - `prefix` (string)
 
 If a required parameter is missing from `$ARGUMENTS`, ask before calling — do not invent values. Coerce each value to its JSON type (booleans → true/false, numbers → numeric, object/array → parse JSON), then make the single tool call and summarize the result.

package/.claude/commands/drupal-config-set.md

@@ -15,6 +15,6 @@ Parse the request in `$ARGUMENTS` into this tool's parameters:
 - `value` (object (pass as JSON)): A map of top-level config keys to their new values (e.g. { "slogan": "Information Technology" }). Other keys in the object are preserved server-side.
 
 **Optional:**
-- `site` (string): omit for the default site
+- `site` (string): Named site from connector config. Omit only on reads: multi-site configs fall back to defaultSite (often local/dev, not production). Writes require an explicit site when more than one site is configured. Every response includes `_target` { name, baseUrl, source } (`hint` when you passed site, `default` when you did not).
 
 If a required parameter is missing from `$ARGUMENTS`, ask before calling — do not invent values. Coerce each value to its JSON type (booleans → true/false, numbers → numeric, object/array → parse JSON), then make the single tool call and summarize the result.

package/.claude/commands/drupal-content-by-moderation-state.md

@@ -1,12 +1,12 @@
 ---
-description: "List nodes of a content type currently in a given moderation state (e.g. what is in 'draft' or 'needs_review')."
+description: "List nodes of a content type currently in a given moderation state (e.g. what is in 'draft' or 'needs_review'). Stock JSON:API cannot filter the computed moderation_state field; when the site rejects that filter the tool samples recent nodes client-side and marks the result approximate, instead of returning Drupal's 500."
 argument-hint: "<type> <state> [site] [limit] [offset]"
 allowed-tools: mcp__drupal__drupal_content_by_moderation_state
 ---
 
 Call the `mcp__drupal__drupal_content_by_moderation_state` MCP tool.
 
-List nodes of a content type currently in a given moderation state (e.g. what is in 'draft' or 'needs_review').
+List nodes of a content type currently in a given moderation state (e.g. what is in 'draft' or 'needs_review'). Stock JSON:API cannot filter the computed moderation_state field; when the site rejects that filter the tool samples recent nodes client-side and marks the result approximate, instead of returning Drupal's 500.
 
 Parse the request in `$ARGUMENTS` into this tool's parameters:
 
@@ -15,7 +15,7 @@ Parse the request in `$ARGUMENTS` into this tool's parameters:
 - `state` (string): Moderation state machine name
 
 **Optional:**
-- `site` (string): omit for the default site
+- `site` (string): Named site from connector config. Omit only on reads: multi-site configs fall back to defaultSite (often local/dev, not production). Writes require an explicit site when more than one site is configured. Every response includes `_target` { name, baseUrl, source } (`hint` when you passed site, `default` when you did not).
 - `limit` (number)
 - `offset` (number)
 

package/.claude/commands/drupal-create-block.md

@@ -15,7 +15,7 @@ Parse the request in `$ARGUMENTS` into this tool's parameters:
 - `info` (string): Administrative label / block description
 
 **Optional:**
-- `site` (string): omit for the default site
+- `site` (string): Named site from connector config. Omit only on reads: multi-site configs fall back to defaultSite (often local/dev, not production). Writes require an explicit site when more than one site is configured. Every response includes `_target` { name, baseUrl, source } (`hint` when you passed site, `default` when you did not).
 - `body` (string): Block body HTML (optional)
 
 If a required parameter is missing from `$ARGUMENTS`, ask before calling — do not invent values. Coerce each value to its JSON type (booleans → true/false, numbers → numeric, object/array → parse JSON), then make the single tool call and summarize the result.

package/.claude/commands/drupal-create-media.md

@@ -15,7 +15,7 @@ Parse the request in `$ARGUMENTS` into this tool's parameters:
 - `name` (string): Media entity name / label
 
 **Optional:**
-- `site` (string): omit for the default site
+- `site` (string): Named site from connector config. Omit only on reads: multi-site configs fall back to defaultSite (often local/dev, not production). Writes require an explicit site when more than one site is configured. Every response includes `_target` { name, baseUrl, source } (`hint` when you passed site, `default` when you did not).
 - `status` (boolean (true/false)): Published flag. Defaults to false (unpublished). Requires allowPublish when true.
 - `fields` (object (pass as JSON)): Additional field values — include the source field (e.g. field_media_oembed_video: 'https://youtu.be/...'). Entity-reference values in JSON:API linkage shape ({ data: { type, id } }) are sent as relationships automatically.
 

package/.claude/commands/drupal-create-menu-link.md

@@ -16,7 +16,7 @@ Parse the request in `$ARGUMENTS` into this tool's parameters:
 - `menu` (string): Menu machine name to place the link in, e.g. 'main' or 'footer'
 
 **Optional:**
-- `site` (string): omit for the default site
+- `site` (string): Named site from connector config. Omit only on reads: multi-site configs fall back to defaultSite (often local/dev, not production). Writes require an explicit site when more than one site is configured. Every response includes `_target` { name, baseUrl, source } (`hint` when you passed site, `default` when you did not).
 - `weight` (number): Ordering weight within the menu (lower sorts first)
 - `parent` (string): Parent link plugin id to nest under, e.g. 'menu_link_content:<uuid>'. Omit for a top-level link.
 - `enabled` (boolean (true/false)): Whether the link is enabled (renders). Defaults to true.

package/.claude/commands/drupal-create-node.md

@@ -15,7 +15,7 @@ Parse the request in `$ARGUMENTS` into this tool's parameters:
 - `title` (string)
 
 **Optional:**
-- `site` (string): omit for the default site
+- `site` (string): Named site from connector config. Omit only on reads: multi-site configs fall back to defaultSite (often local/dev, not production). Writes require an explicit site when more than one site is configured. Every response includes `_target` { name, baseUrl, source } (`hint` when you passed site, `default` when you did not).
 - `body` (string): Body field HTML
 - `summary` (string): Body summary/teaser — writes the `summary` property of the body field (core `text_with_summary`). Many headless sites instead use a dedicated summary/deck field for teasers and meta descriptions; on those, set that field in `fields` — a value written here will be stored but may never be rendered.
 - `format` (string): Text format machine name for the body, e.g. 'basic_html'. Defaults to the site config's `defaultTextFormat`, then 'full_html'. Set this when the site's formats do not include full_html, or to avoid writing content into a more permissive format than intended.

package/.claude/commands/drupal-create-paragraph.md

@@ -14,7 +14,7 @@ Parse the request in `$ARGUMENTS` into this tool's parameters:
 - `paragraphType` (string): Paragraph type / bundle machine name, e.g. 'text', 'image', 'cta'
 
 **Optional:**
-- `site` (string): Named site (omit for default)
+- `site` (string): Named site from connector config. Omit only on reads: multi-site configs fall back to defaultSite (often local/dev, not production). Writes require an explicit site when more than one site is configured. Every response includes `_target` { name, baseUrl, source } (`hint` when you passed site, `default` when you did not).
 - `attributes` (object (pass as JSON)): Paragraph field values keyed by Drupal machine name, e.g. { field_body: { value: '<p>..</p>', format: 'full_html' } }
 
 If a required parameter is missing from `$ARGUMENTS`, ask before calling — do not invent values. Coerce each value to its JSON type (booleans → true/false, numbers → numeric, object/array → parse JSON), then make the single tool call and summarize the result.

package/.claude/commands/drupal-create-redirect.md

@@ -15,7 +15,7 @@ Parse the request in `$ARGUMENTS` into this tool's parameters:
 - `target` (string): Destination: a path ('/new-slug'), 'entity:node/42', or an absolute 'https://…' URL.
 
 **Optional:**
-- `site` (string): Named site (omit for default)
+- `site` (string): Named site from connector config. Omit only on reads: multi-site configs fall back to defaultSite (often local/dev, not production). Writes require an explicit site when more than one site is configured. Every response includes `_target` { name, baseUrl, source } (`hint` when you passed site, `default` when you did not).
 - `statusCode` (number): HTTP redirect status code. 301 (permanent, default) or 302 (temporary); 303/307/308 also accepted.
 - `language` (string): Langcode the redirect applies to. Defaults to 'und' (all languages).
 

package/.claude/commands/drupal-create-taxonomy-term.md

@@ -15,7 +15,7 @@ Parse the request in `$ARGUMENTS` into this tool's parameters:
 - `name` (string)
 
 **Optional:**
-- `site` (string): omit for the default site
+- `site` (string): Named site from connector config. Omit only on reads: multi-site configs fall back to defaultSite (often local/dev, not production). Writes require an explicit site when more than one site is configured. Every response includes `_target` { name, baseUrl, source } (`hint` when you passed site, `default` when you did not).
 - `description` (string)
 - `weight` (number)
 - `parentId` (string): UUID of parent term (for hierarchical vocabularies)

package/.claude/commands/drupal-create-translation.md

@@ -16,7 +16,7 @@ Parse the request in `$ARGUMENTS` into this tool's parameters:
 - `langcode` (string): Target language code, e.g. 'de', 'fr', 'pt_br'
 
 **Optional:**
-- `site` (string): omit for the default site
+- `site` (string): Named site from connector config. Omit only on reads: multi-site configs fall back to defaultSite (often local/dev, not production). Writes require an explicit site when more than one site is configured. Every response includes `_target` { name, baseUrl, source } (`hint` when you passed site, `default` when you did not).
 - `entityType` (string): Entity type machine name. Default: 'node'.
 - `attributes` (object (pass as JSON)): Translated field values keyed by Drupal machine name
 

package/.claude/commands/drupal-create-user.md

@@ -15,7 +15,7 @@ Parse the request in `$ARGUMENTS` into this tool's parameters:
 - `mail` (string): Email address
 
 **Optional:**
-- `site` (string): omit for the default site
+- `site` (string): Named site from connector config. Omit only on reads: multi-site configs fall back to defaultSite (often local/dev, not production). Writes require an explicit site when more than one site is configured. Every response includes `_target` { name, baseUrl, source } (`hint` when you passed site, `default` when you did not).
 - `password` (string): Initial password (plaintext — sent over HTTPS)
 - `status` (boolean (true/false)): true = active (default)
 - `roles` (array (pass as JSON)): Role UUIDs to assign

package/.claude/commands/drupal-delete-media.md

@@ -17,6 +17,6 @@ Parse the request in `$ARGUMENTS` into this tool's parameters:
 - `id` (string)
 
 **Optional:**
-- `site` (string): omit for the default site
+- `site` (string): Named site from connector config. Omit only on reads: multi-site configs fall back to defaultSite (often local/dev, not production). Writes require an explicit site when more than one site is configured. Every response includes `_target` { name, baseUrl, source } (`hint` when you passed site, `default` when you did not).
 
 If a required parameter is missing from `$ARGUMENTS`, ask before calling — do not invent values. Coerce each value to its JSON type (booleans → true/false, numbers → numeric, object/array → parse JSON), then make the single tool call and summarize the result.

package/.claude/commands/drupal-delete-node.md

@@ -17,7 +17,7 @@ Parse the request in `$ARGUMENTS` into this tool's parameters:
 - `id` (string): Node UUID
 
 **Optional:**
-- `site` (string): omit for the default site
+- `site` (string): Named site from connector config. Omit only on reads: multi-site configs fall back to defaultSite (often local/dev, not production). Writes require an explicit site when more than one site is configured. Every response includes `_target` { name, baseUrl, source } (`hint` when you passed site, `default` when you did not).
 - `dryRun` (boolean (true/false)): Validate and return a preview of the delete without committing.
 
 If a required parameter is missing from `$ARGUMENTS`, ask before calling — do not invent values. Coerce each value to its JSON type (booleans → true/false, numbers → numeric, object/array → parse JSON), then make the single tool call and summarize the result.

package/.claude/commands/drupal-delete-taxonomy-term.md

@@ -17,6 +17,6 @@ Parse the request in `$ARGUMENTS` into this tool's parameters:
 - `id` (string)
 
 **Optional:**
-- `site` (string): omit for the default site
+- `site` (string): Named site from connector config. Omit only on reads: multi-site configs fall back to defaultSite (often local/dev, not production). Writes require an explicit site when more than one site is configured. Every response includes `_target` { name, baseUrl, source } (`hint` when you passed site, `default` when you did not).
 
 If a required parameter is missing from `$ARGUMENTS`, ask before calling — do not invent values. Coerce each value to its JSON type (booleans → true/false, numbers → numeric, object/array → parse JSON), then make the single tool call and summarize the result.

package/.claude/commands/drupal-describe-fields.md

@@ -11,7 +11,7 @@ Introspect the fields of a Drupal entity type + bundle: returns a per-field list
 Parse the request in `$ARGUMENTS` into this tool's parameters:
 
 **Required:**
-- `site` (string): Configured site name.
+- `site` (string): Named site from connector config. Omit only on reads: multi-site configs fall back to defaultSite (often local/dev, not production). Writes require an explicit site when more than one site is configured. Every response includes `_target` { name, baseUrl, source } (`hint` when you passed site, `default` when you did not).
 
 **Optional:**
 - `type` (string): Entity type machine name, e.g. 'node', 'taxonomy_term', 'user', 'media'. Alias: `entityType` (as used by the sibling tools).

package/.claude/commands/drupal-drush-cache-rebuild.md

@@ -11,6 +11,6 @@ Run `drush cache:rebuild` via SSH. Clears all Drupal caches. Requires drushSsh c
 Parse the request in `$ARGUMENTS` into this tool's parameters:
 
 **Optional:**
-- `site` (string): omit for the default site
+- `site` (string): Named site from connector config. Omit only on reads: multi-site configs fall back to defaultSite (often local/dev, not production). Writes require an explicit site when more than one site is configured. Every response includes `_target` { name, baseUrl, source } (`hint` when you passed site, `default` when you did not).
 
 If a required parameter is missing from `$ARGUMENTS`, ask before calling — do not invent values. Coerce each value to its JSON type (booleans → true/false, numbers → numeric, object/array → parse JSON), then make the single tool call and summarize the result.

package/.claude/commands/drupal-drush-config-export.md

@@ -11,6 +11,6 @@ Export active configuration to the sync directory. Requires write access.
 Parse the request in `$ARGUMENTS` into this tool's parameters:
 
 **Optional:**
-- `site` (string): omit for the default site
+- `site` (string): Named site from connector config. Omit only on reads: multi-site configs fall back to defaultSite (often local/dev, not production). Writes require an explicit site when more than one site is configured. Every response includes `_target` { name, baseUrl, source } (`hint` when you passed site, `default` when you did not).
 
 If a required parameter is missing from `$ARGUMENTS`, ask before calling — do not invent values. Coerce each value to its JSON type (booleans → true/false, numbers → numeric, object/array → parse JSON), then make the single tool call and summarize the result.

package/.claude/commands/drupal-drush-config-import.md

@@ -11,6 +11,6 @@ Import configuration from the sync directory into the database. Requires write a
 Parse the request in `$ARGUMENTS` into this tool's parameters:
 
 **Optional:**
-- `site` (string): omit for the default site
+- `site` (string): Named site from connector config. Omit only on reads: multi-site configs fall back to defaultSite (often local/dev, not production). Writes require an explicit site when more than one site is configured. Every response includes `_target` { name, baseUrl, source } (`hint` when you passed site, `default` when you did not).
 
 If a required parameter is missing from `$ARGUMENTS`, ask before calling — do not invent values. Coerce each value to its JSON type (booleans → true/false, numbers → numeric, object/array → parse JSON), then make the single tool call and summarize the result.

package/.claude/commands/drupal-drush-config-status.md

@@ -11,6 +11,6 @@ Check if active config is in sync with the sync directory. Returns out-of-sync i
 Parse the request in `$ARGUMENTS` into this tool's parameters:
 
 **Optional:**
-- `site` (string): omit for the default site
+- `site` (string): Named site from connector config. Omit only on reads: multi-site configs fall back to defaultSite (often local/dev, not production). Writes require an explicit site when more than one site is configured. Every response includes `_target` { name, baseUrl, source } (`hint` when you passed site, `default` when you did not).
 
 If a required parameter is missing from `$ARGUMENTS`, ask before calling — do not invent values. Coerce each value to its JSON type (booleans → true/false, numbers → numeric, object/array → parse JSON), then make the single tool call and summarize the result.

package/.claude/commands/drupal-drush-cron.md

@@ -11,6 +11,6 @@ Run Drupal cron via `drush cron`.
 Parse the request in `$ARGUMENTS` into this tool's parameters:
 
 **Optional:**
-- `site` (string): omit for the default site
+- `site` (string): Named site from connector config. Omit only on reads: multi-site configs fall back to defaultSite (often local/dev, not production). Writes require an explicit site when more than one site is configured. Every response includes `_target` { name, baseUrl, source } (`hint` when you passed site, `default` when you did not).
 
 If a required parameter is missing from `$ARGUMENTS`, ask before calling — do not invent values. Coerce each value to its JSON type (booleans → true/false, numbers → numeric, object/array → parse JSON), then make the single tool call and summarize the result.

package/.claude/commands/drupal-drush-module-disable.md

@@ -16,6 +16,6 @@ Parse the request in `$ARGUMENTS` into this tool's parameters:
 - `moduleName` (string)
 
 **Optional:**
-- `site` (string): omit for the default site
+- `site` (string): Named site from connector config. Omit only on reads: multi-site configs fall back to defaultSite (often local/dev, not production). Writes require an explicit site when more than one site is configured. Every response includes `_target` { name, baseUrl, source } (`hint` when you passed site, `default` when you did not).
 
 If a required parameter is missing from `$ARGUMENTS`, ask before calling — do not invent values. Coerce each value to its JSON type (booleans → true/false, numbers → numeric, object/array → parse JSON), then make the single tool call and summarize the result.

package/.claude/commands/drupal-drush-module-enable.md

@@ -14,6 +14,6 @@ Parse the request in `$ARGUMENTS` into this tool's parameters:
 - `moduleName` (string)
 
 **Optional:**
-- `site` (string): omit for the default site
+- `site` (string): Named site from connector config. Omit only on reads: multi-site configs fall back to defaultSite (often local/dev, not production). Writes require an explicit site when more than one site is configured. Every response includes `_target` { name, baseUrl, source } (`hint` when you passed site, `default` when you did not).
 
 If a required parameter is missing from `$ARGUMENTS`, ask before calling — do not invent values. Coerce each value to its JSON type (booleans → true/false, numbers → numeric, object/array → parse JSON), then make the single tool call and summarize the result.

package/.claude/commands/drupal-drush-module-list.md

@@ -11,7 +11,7 @@ List Drupal modules. Filter by enabled or disabled status.
 Parse the request in `$ARGUMENTS` into this tool's parameters:
 
 **Optional:**
-- `site` (string): omit for the default site
+- `site` (string): Named site from connector config. Omit only on reads: multi-site configs fall back to defaultSite (often local/dev, not production). Writes require an explicit site when more than one site is configured. Every response includes `_target` { name, baseUrl, source } (`hint` when you passed site, `default` when you did not).
 - `status` (string)
 
 If a required parameter is missing from `$ARGUMENTS`, ask before calling — do not invent values. Coerce each value to its JSON type (booleans → true/false, numbers → numeric, object/array → parse JSON), then make the single tool call and summarize the result.

package/.claude/commands/drupal-drush-security-updates.md

@@ -11,6 +11,6 @@ List modules with known security advisories via `drush pm:security`.
 Parse the request in `$ARGUMENTS` into this tool's parameters:
 
 **Optional:**
-- `site` (string): omit for the default site
+- `site` (string): Named site from connector config. Omit only on reads: multi-site configs fall back to defaultSite (often local/dev, not production). Writes require an explicit site when more than one site is configured. Every response includes `_target` { name, baseUrl, source } (`hint` when you passed site, `default` when you did not).
 
 If a required parameter is missing from `$ARGUMENTS`, ask before calling — do not invent values. Coerce each value to its JSON type (booleans → true/false, numbers → numeric, object/array → parse JSON), then make the single tool call and summarize the result.

package/.claude/commands/drupal-drush-sql-query.md

@@ -14,6 +14,6 @@ Parse the request in `$ARGUMENTS` into this tool's parameters:
 - `query` (string)
 
 **Optional:**
-- `site` (string): omit for the default site
+- `site` (string): Named site from connector config. Omit only on reads: multi-site configs fall back to defaultSite (often local/dev, not production). Writes require an explicit site when more than one site is configured. Every response includes `_target` { name, baseUrl, source } (`hint` when you passed site, `default` when you did not).
 
 If a required parameter is missing from `$ARGUMENTS`, ask before calling — do not invent values. Coerce each value to its JSON type (booleans → true/false, numbers → numeric, object/array → parse JSON), then make the single tool call and summarize the result.

package/.claude/commands/drupal-drush-status.md

@@ -11,6 +11,6 @@ Get Drupal site status via `drush status` — version, DB, file paths, active co
 Parse the request in `$ARGUMENTS` into this tool's parameters:
 
 **Optional:**
-- `site` (string): omit for the default site
+- `site` (string): Named site from connector config. Omit only on reads: multi-site configs fall back to defaultSite (often local/dev, not production). Writes require an explicit site when more than one site is configured. Every response includes `_target` { name, baseUrl, source } (`hint` when you passed site, `default` when you did not).
 
 If a required parameter is missing from `$ARGUMENTS`, ask before calling — do not invent values. Coerce each value to its JSON type (booleans → true/false, numbers → numeric, object/array → parse JSON), then make the single tool call and summarize the result.

package/.claude/commands/drupal-drush-updatedb.md

@@ -11,6 +11,6 @@ Run pending database updates via `drush updatedb`. Always run after deploying mo
 Parse the request in `$ARGUMENTS` into this tool's parameters:
 
 **Optional:**
-- `site` (string): omit for the default site
+- `site` (string): Named site from connector config. Omit only on reads: multi-site configs fall back to defaultSite (often local/dev, not production). Writes require an explicit site when more than one site is configured. Every response includes `_target` { name, baseUrl, source } (`hint` when you passed site, `default` when you did not).
 
 If a required parameter is missing from `$ARGUMENTS`, ask before calling — do not invent values. Coerce each value to its JSON type (booleans → true/false, numbers → numeric, object/array → parse JSON), then make the single tool call and summarize the result.

package/.claude/commands/drupal-drush-user-create.md

@@ -16,7 +16,7 @@ Parse the request in `$ARGUMENTS` into this tool's parameters:
 - `password` (string)
 
 **Optional:**
-- `site` (string): omit for the default site
+- `site` (string): Named site from connector config. Omit only on reads: multi-site configs fall back to defaultSite (often local/dev, not production). Writes require an explicit site when more than one site is configured. Every response includes `_target` { name, baseUrl, source } (`hint` when you passed site, `default` when you did not).
 - `roles` (array (pass as JSON))
 
 If a required parameter is missing from `$ARGUMENTS`, ask before calling — do not invent values. Coerce each value to its JSON type (booleans → true/false, numbers → numeric, object/array → parse JSON), then make the single tool call and summarize the result.

package/.claude/commands/drupal-drush-user-list.md

@@ -11,7 +11,7 @@ List Drupal users via Drush. Filter by active/blocked status or role.
 Parse the request in `$ARGUMENTS` into this tool's parameters:
 
 **Optional:**
-- `site` (string): omit for the default site
+- `site` (string): Named site from connector config. Omit only on reads: multi-site configs fall back to defaultSite (often local/dev, not production). Writes require an explicit site when more than one site is configured. Every response includes `_target` { name, baseUrl, source } (`hint` when you passed site, `default` when you did not).
 - `status` (string)
 - `role` (string)
 - `limit` (number)

package/.claude/commands/drupal-drush-watchdog.md

@@ -11,7 +11,7 @@ Fetch recent Drupal watchdog/dblog entries. Filter by type or severity level.
 Parse the request in `$ARGUMENTS` into this tool's parameters:
 
 **Optional:**
-- `site` (string): omit for the default site
+- `site` (string): Named site from connector config. Omit only on reads: multi-site configs fall back to defaultSite (often local/dev, not production). Writes require an explicit site when more than one site is configured. Every response includes `_target` { name, baseUrl, source } (`hint` when you passed site, `default` when you did not).
 - `type` (string)
 - `severity` (string)
 - `limit` (number)

package/.claude/commands/drupal-entity-create.md

@@ -15,7 +15,7 @@ Parse the request in `$ARGUMENTS` into this tool's parameters:
 - `bundle` (string)
 
 **Optional:**
-- `site` (string): omit for the default site
+- `site` (string): Named site from connector config. Omit only on reads: multi-site configs fall back to defaultSite (often local/dev, not production). Writes require an explicit site when more than one site is configured. Every response includes `_target` { name, baseUrl, source } (`hint` when you passed site, `default` when you did not).
 - `attributes` (object (pass as JSON)): Field values keyed by Drupal machine name
 - `relationships` (object (pass as JSON)): Relationship data keyed by field name
 - `dryRun` (boolean (true/false)): Validate and return a preview of the create without committing.

package/.claude/commands/drupal-entity-delete.md

@@ -18,7 +18,7 @@ Parse the request in `$ARGUMENTS` into this tool's parameters:
 - `id` (string)
 
 **Optional:**
-- `site` (string): omit for the default site
+- `site` (string): Named site from connector config. Omit only on reads: multi-site configs fall back to defaultSite (often local/dev, not production). Writes require an explicit site when more than one site is configured. Every response includes `_target` { name, baseUrl, source } (`hint` when you passed site, `default` when you did not).
 - `dryRun` (boolean (true/false)): Validate and return a preview of the delete without committing.
 
 If a required parameter is missing from `$ARGUMENTS`, ask before calling — do not invent values. Coerce each value to its JSON type (booleans → true/false, numbers → numeric, object/array → parse JSON), then make the single tool call and summarize the result.

package/.claude/commands/drupal-entity-get.md

@@ -16,7 +16,7 @@ Parse the request in `$ARGUMENTS` into this tool's parameters:
 - `id` (string): Entity UUID
 
 **Optional:**
-- `site` (string): omit for the default site
+- `site` (string): Named site from connector config. Omit only on reads: multi-site configs fall back to defaultSite (often local/dev, not production). Writes require an explicit site when more than one site is configured. Every response includes `_target` { name, baseUrl, source } (`hint` when you passed site, `default` when you did not).
 - `include` (array (pass as JSON)): Relationship field names to sideload
 
 If a required parameter is missing from `$ARGUMENTS`, ask before calling — do not invent values. Coerce each value to its JSON type (booleans → true/false, numbers → numeric, object/array → parse JSON), then make the single tool call and summarize the result.

package/.claude/commands/drupal-entity-list.md

@@ -15,7 +15,7 @@ Parse the request in `$ARGUMENTS` into this tool's parameters:
 - `bundle` (string): Bundle machine name
 
 **Optional:**
-- `site` (string): omit for the default site
+- `site` (string): Named site from connector config. Omit only on reads: multi-site configs fall back to defaultSite (often local/dev, not production). Writes require an explicit site when more than one site is configured. Every response includes `_target` { name, baseUrl, source } (`hint` when you passed site, `default` when you did not).
 - `filters` (array (pass as JSON)): Structured filters: [{ field, op, value }]
 - `sort` (array (pass as JSON)): Sort specs: [{ field, dir }]
 - `include` (array (pass as JSON)): Relationship field names to sideload

package/.claude/commands/drupal-entity-update.md

@@ -16,7 +16,7 @@ Parse the request in `$ARGUMENTS` into this tool's parameters:
 - `id` (string)
 
 **Optional:**
-- `site` (string): omit for the default site
+- `site` (string): Named site from connector config. Omit only on reads: multi-site configs fall back to defaultSite (often local/dev, not production). Writes require an explicit site when more than one site is configured. Every response includes `_target` { name, baseUrl, source } (`hint` when you passed site, `default` when you did not).
 - `attributes` (object (pass as JSON))
 - `relationships` (object (pass as JSON))
 - `dryRun` (boolean (true/false)): Validate, resolve ERR identifiers, and (on moderated targets) run the core PATCH-guard probe against Drupal, then return a preview without the real write. The probe uses a non-matching data.id so Drupal does not save. A working-copy 400 fails the dryRun.

package/.claude/commands/drupal-find-orphaned-media.md

@@ -11,7 +11,7 @@ Find media entities not referenced by any content. Useful for storage cleanup au
 Parse the request in `$ARGUMENTS` into this tool's parameters:
 
 **Optional:**
-- `site` (string): omit for the default site
+- `site` (string): Named site from connector config. Omit only on reads: multi-site configs fall back to defaultSite (often local/dev, not production). Writes require an explicit site when more than one site is configured. Every response includes `_target` { name, baseUrl, source } (`hint` when you passed site, `default` when you did not).
 - `type` (string): Media type to check (default: image)
 - `limit` (number)
 

package/.claude/commands/drupal-get-entity-schema.md

@@ -15,6 +15,6 @@ Parse the request in `$ARGUMENTS` into this tool's parameters:
 - `bundle` (string): e.g. 'article', 'text', 'default'
 
 **Optional:**
-- `site` (string): omit for the default site
+- `site` (string): Named site from connector config. Omit only on reads: multi-site configs fall back to defaultSite (often local/dev, not production). Writes require an explicit site when more than one site is configured. Every response includes `_target` { name, baseUrl, source } (`hint` when you passed site, `default` when you did not).
 
 If a required parameter is missing from `$ARGUMENTS`, ask before calling — do not invent values. Coerce each value to its JSON type (booleans → true/false, numbers → numeric, object/array → parse JSON), then make the single tool call and summarize the result.

package/.claude/commands/drupal-get-media.md

@@ -15,6 +15,6 @@ Parse the request in `$ARGUMENTS` into this tool's parameters:
 - `id` (string): Media entity UUID
 
 **Optional:**
-- `site` (string): omit for the default site
+- `site` (string): Named site from connector config. Omit only on reads: multi-site configs fall back to defaultSite (often local/dev, not production). Writes require an explicit site when more than one site is configured. Every response includes `_target` { name, baseUrl, source } (`hint` when you passed site, `default` when you did not).
 
 If a required parameter is missing from `$ARGUMENTS`, ask before calling — do not invent values. Coerce each value to its JSON type (booleans → true/false, numbers → numeric, object/array → parse JSON), then make the single tool call and summarize the result.

package/.claude/commands/drupal-get-node.md

@@ -15,6 +15,6 @@ Parse the request in `$ARGUMENTS` into this tool's parameters:
 - `id` (string): Node UUID
 
 **Optional:**
-- `site` (string): Named site (omit for default)
+- `site` (string): Named site from connector config. Omit only on reads: multi-site configs fall back to defaultSite (often local/dev, not production). Writes require an explicit site when more than one site is configured. Every response includes `_target` { name, baseUrl, source } (`hint` when you passed site, `default` when you did not).
 
 If a required parameter is missing from `$ARGUMENTS`, ask before calling — do not invent values. Coerce each value to its JSON type (booleans → true/false, numbers → numeric, object/array → parse JSON), then make the single tool call and summarize the result.

package/.claude/commands/drupal-get-paragraph.md

@@ -15,6 +15,6 @@ Parse the request in `$ARGUMENTS` into this tool's parameters:
 - `id` (string): Paragraph UUID
 
 **Optional:**
-- `site` (string): omit for the default site
+- `site` (string): Named site from connector config. Omit only on reads: multi-site configs fall back to defaultSite (often local/dev, not production). Writes require an explicit site when more than one site is configured. Every response includes `_target` { name, baseUrl, source } (`hint` when you passed site, `default` when you did not).
 
 If a required parameter is missing from `$ARGUMENTS`, ask before calling — do not invent values. Coerce each value to its JSON type (booleans → true/false, numbers → numeric, object/array → parse JSON), then make the single tool call and summarize the result.

package/.claude/commands/drupal-get-revision.md

@@ -16,6 +16,6 @@ Parse the request in `$ARGUMENTS` into this tool's parameters:
 - `version` (string): Numeric vid, 'id:<vid>', 'rel:latest-version', or 'rel:working-copy'.
 
 **Optional:**
-- `site` (string): omit for the default site
+- `site` (string): Named site from connector config. Omit only on reads: multi-site configs fall back to defaultSite (often local/dev, not production). Writes require an explicit site when more than one site is configured. Every response includes `_target` { name, baseUrl, source } (`hint` when you passed site, `default` when you did not).
 
 If a required parameter is missing from `$ARGUMENTS`, ask before calling — do not invent values. Coerce each value to its JSON type (booleans → true/false, numbers → numeric, object/array → parse JSON), then make the single tool call and summarize the result.

package/.claude/commands/drupal-get-taxonomy-term.md

@@ -15,6 +15,6 @@ Parse the request in `$ARGUMENTS` into this tool's parameters:
 - `id` (string): Term UUID
 
 **Optional:**
-- `site` (string): omit for the default site
+- `site` (string): Named site from connector config. Omit only on reads: multi-site configs fall back to defaultSite (often local/dev, not production). Writes require an explicit site when more than one site is configured. Every response includes `_target` { name, baseUrl, source } (`hint` when you passed site, `default` when you did not).
 
 If a required parameter is missing from `$ARGUMENTS`, ask before calling — do not invent values. Coerce each value to its JSON type (booleans → true/false, numbers → numeric, object/array → parse JSON), then make the single tool call and summarize the result.

package/.claude/commands/drupal-get-taxonomy-terms.md

@@ -14,7 +14,7 @@ Parse the request in `$ARGUMENTS` into this tool's parameters:
 - `vocabulary` (string): Vocabulary machine name, e.g. 'tags'
 
 **Optional:**
-- `site` (string): omit for the default site
+- `site` (string): Named site from connector config. Omit only on reads: multi-site configs fall back to defaultSite (often local/dev, not production). Writes require an explicit site when more than one site is configured. Every response includes `_target` { name, baseUrl, source } (`hint` when you passed site, `default` when you did not).
 - `limit` (number)
 - `offset` (number)
 

package/.claude/commands/drupal-get-user-by-name.md

@@ -14,6 +14,6 @@ Parse the request in `$ARGUMENTS` into this tool's parameters:
 - `name` (string): Drupal username (exact match)
 
 **Optional:**
-- `site` (string): omit for the default site
+- `site` (string): Named site from connector config. Omit only on reads: multi-site configs fall back to defaultSite (often local/dev, not production). Writes require an explicit site when more than one site is configured. Every response includes `_target` { name, baseUrl, source } (`hint` when you passed site, `default` when you did not).
 
 If a required parameter is missing from `$ARGUMENTS`, ask before calling — do not invent values. Coerce each value to its JSON type (booleans → true/false, numbers → numeric, object/array → parse JSON), then make the single tool call and summarize the result.

package/.claude/commands/drupal-get-user.md

@@ -14,6 +14,6 @@ Parse the request in `$ARGUMENTS` into this tool's parameters:
 - `id` (string): User UUID
 
 **Optional:**
-- `site` (string): omit for the default site
+- `site` (string): Named site from connector config. Omit only on reads: multi-site configs fall back to defaultSite (often local/dev, not production). Writes require an explicit site when more than one site is configured. Every response includes `_target` { name, baseUrl, source } (`hint` when you passed site, `default` when you did not).
 
 If a required parameter is missing from `$ARGUMENTS`, ask before calling — do not invent values. Coerce each value to its JSON type (booleans → true/false, numbers → numeric, object/array → parse JSON), then make the single tool call and summarize the result.

package/.claude/commands/drupal-governance-status.md

@@ -11,6 +11,6 @@ Report each configured site's source-governance condition. Always probes GET /dr
 Parse the request in `$ARGUMENTS` into this tool's parameters:
 
 **Optional:**
-- `site` (string): omit for the default site
+- `site` (string): Named site from connector config. Omit only on reads: multi-site configs fall back to defaultSite (often local/dev, not production). Writes require an explicit site when more than one site is configured. Every response includes `_target` { name, baseUrl, source } (`hint` when you passed site, `default` when you did not).
 
 If a required parameter is missing from `$ARGUMENTS`, ask before calling — do not invent values. Coerce each value to its JSON type (booleans → true/false, numbers → numeric, object/array → parse JSON), then make the single tool call and summarize the result.

package/.claude/commands/drupal-graphql-introspect.md

@@ -11,7 +11,7 @@ Introspect the Drupal GraphQL schema. Omit typeName for a full schema overview;
 Parse the request in `$ARGUMENTS` into this tool's parameters:
 
 **Optional:**
-- `site` (string): omit for the default site
+- `site` (string): Named site from connector config. Omit only on reads: multi-site configs fall back to defaultSite (often local/dev, not production). Writes require an explicit site when more than one site is configured. Every response includes `_target` { name, baseUrl, source } (`hint` when you passed site, `default` when you did not).
 - `typeName` (string): Name of a specific GraphQL type to inspect in detail (optional)
 
 If a required parameter is missing from `$ARGUMENTS`, ask before calling — do not invent values. Coerce each value to its JSON type (booleans → true/false, numbers → numeric, object/array → parse JSON), then make the single tool call and summarize the result.

package/.claude/commands/drupal-graphql.md

@@ -35,7 +35,7 @@ Parse the request in `$ARGUMENTS` into this tool's parameters:
 - `query` (string): GraphQL query or mutation string
 
 **Optional:**
-- `site` (string): Named site (omit for default)
+- `site` (string): Named site from connector config. Omit only on reads: multi-site configs fall back to defaultSite (often local/dev, not production). Writes require an explicit site when more than one site is configured. Every response includes `_target` { name, baseUrl, source } (`hint` when you passed site, `default` when you did not).
 - `variables` (object (pass as JSON)): Variables to pass with the query
 - `operationName` (string): Operation name (for multi-operation documents)