@digestseo/mcp-gsc 0.4.11 → 0.4.13

package/CHANGELOG.md

@@ -7,6 +7,20 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
 
 ## [Unreleased]
 
+## [0.4.13] - 2026-09-22
+
+### Fixed
+- The published `npx` launcher now persists local Wrangler/KV/Durable Object state in a stable per-user directory instead of the versioned npm package cache, preserving the encrypted Google session across later package upgrades and ordinary npm cache cleanup; `MCP_GSC_STATE_DIR` can override the location. The first release with this change may require one Google reconnect because older launcher releases used the package cache for local state.
+- Official MCP Registry discovery no longer advertises the owner-hosted remote while that deployment's tool contract lags the current npm package; the verified npm launcher remains the Registry installation path until hosted parity is restored.
+- Search Analytics now exposes a machine-readable Generative AI report boundary instead of inviting agents to invent an unsupported selector: the current documented API has no dedicated Generative AI search type/filter, while AI Overviews and AI Mode remain included in overall web Search performance data.
+
+## [0.4.12] - 2026-09-22
+
+### Fixed
+- `urls.inspect_many` now runs URL Inspection requests with bounded concurrency of three instead of strictly sequentially, reducing batch latency while preserving per-URL safety-budget accounting, input-order results, per-URL failures, and batch-fatal Google-access revocation.
+- Search Analytics now rejects `searchAppearance` combined with another grouping dimension and documents Google's required two-step appearance discovery/filter workflow instead of sending invalid grouped requests to the provider.
+- Brand/non-brand Search Analytics guidance now distinguishes caller-supplied regex segmentation from Search Console's AI-assisted native Branded/Non-branded filter, which the Search Analytics API does not expose.
+
 ## [0.4.11] - 2026-09-22
 
 ### Fixed

package/README.md

@@ -24,6 +24,8 @@ npx -y @digestseo/mcp-gsc
 
 The npm launcher starts a loopback-only **Streamable HTTP** Worker on `127.0.0.1` (port `8080` by default); it is not a stdio MCP process. You can run the `npx` command from any directory because the launcher resolves its bundled Worker configuration from the installed package. Clients that launch the package should connect to `http://127.0.0.1:8080/mcp` after supplying the Google OAuth and token-encryption environment variables described in [SETUP.md](SETUP.md). Before the first OAuth sign-in, authorize the exact callback `http://127.0.0.1:8080/google/callback` in Google Cloud (or use the same custom `PORT` you launch with); the launcher prints both URLs at startup.
 
+Local KV and Durable Object state, including the encrypted Google session, is stored in `~/.mcp-gsc/state` by default instead of inside the versioned npm cache. That keeps the local connection available across package upgrades and ordinary npm cache cleanup. Set `MCP_GSC_STATE_DIR` to use another directory; keep the same `TOKEN_ENCRYPTION_KEY` when reusing existing state because stored refresh tokens are encrypted with that key. The launcher prints the effective state directory at startup. The first release with this stable path may require one Google reconnect because older launcher releases stored local state under the npm package cache.
+
 The local launcher defaults to `GSC_ACCESS_MODE=readwrite`. For least-privilege analytics/reporting-only use, set `GSC_ACCESS_MODE=readonly` in the environment before running `npx`; the launcher forwards that value into the local Worker so OAuth requests only the read-only Search Console scope and the five mutation tools stay unregistered.
 
 For Google OAuth and Cloudflare deployment configuration, follow [SETUP.md](SETUP.md).
@@ -75,10 +77,10 @@ By default (`GSC_ACCESS_MODE=readwrite`), this server exposes 21 tools. Read-onl
 | **`server.capabilities`** | Read | List every tool this server exposes and report whether your Google connection is currently authenticated (`connected` / `not_connected`). Takes no arguments — a good first call for discovery. |
 | **`sites.list`** | Read | List the Search Console properties the connected Google account can access (`siteUrl`, `permissionLevel`). |
 | **`sites.get`** | Read | Retrieve one exact Search Console property and the connected account's permission level for it. |
-| **`analytics.query`** | Read | Impressions, clicks, CTR, and average position over a date range, with dimensions, filters, safe pagination, and selectable search type. Pass `dimensions: []` for true site totals; Google's aggregate row may omit `keys`. Search Analytics does not guarantee every data row and can return only top rows, so exhausting local pagination is not proof that the provider dataset is exhaustive. For `search_type: "discover"` or `"googleNews"`, `position_supported` is `false`; those reports expose clicks, impressions, and CTR but not average position, and query grouping/filtering is unavailable. |
+| **`analytics.query`** | Read | Impressions, clicks, CTR, and average position over a date range, with dimensions, filters, safe pagination, and selectable search type. Pass `dimensions: []` for true site totals; Google's aggregate row may omit `keys`. Search Analytics does not guarantee every data row and can return only top rows, so exhausting local pagination is not proof that the provider dataset is exhaustive. Search appearance discovery is a two-step workflow: group by `searchAppearance` alone to discover the exact values Google returns for the property, then filter to one returned value in a separate query when grouping by page/query/country/device/date/hour. For `search_type: "discover"` or `"googleNews"`, `position_supported` is `false`; those reports expose clicks, impressions, and CTR but not average position, and query grouping/filtering is unavailable. Search Console's dedicated Generative AI performance reports are not exposed by the current documented Search Analytics API as a dedicated search type or filter selector; `generative_ai_report_isolatable` is therefore `false`. |
 | **`insights.page_queries`** / **`insights.query_pages`** | Read | Drill from one exact page to its Search Console queries, or from one exact query to the pages Google surfaced for it, with `row_limit` / `start_row` pagination. These query-centric helpers support web, image, video, and the Search results News tab; Discover and the Google News report are excluded because they do not expose query data. |
 | **`urls.inspect`** | Read | Google's URL Inspection report for the version of one page currently known in Google's index. It is not a live URL test; mobile-usability output is deprecated. |
-| **`urls.inspect_many`** | Read | Inspect Google's indexed versions of up to 10 URLs sequentially in one call. Each URL still consumes one Google URL Inspection request and one unit of the server's shared inspection safety budget; this does not run live URL tests. |
+| **`urls.inspect_many`** | Read | Inspect Google's indexed versions of up to 10 URLs with bounded concurrency of 3 in one call while preserving input-order results. Each URL still consumes one Google URL Inspection request and one unit of the server's shared inspection safety budget; this does not run live URL tests. |
 | **`sitemaps.list`** / **`sitemaps.get`** | Read | List submitted sitemaps or retrieve one sitemap's details. `lastSubmitted` is when the sitemap was submitted to Search Console; `lastDownloaded` is when Google last downloaded the sitemap. Neither value is the sitemap file's modification/deploy time or a page crawl/indexing timestamp. |
 | **`insights.quick_wins`** / **`insights.cannibalization`** / **`insights.content_decay`** | Read | Surface average-position opportunity rows, query/page overlap, and evidence-ranked click declines. Quick-win candidates are observed query/page rows selected by aggregate Search Console average position, not proof of a stable current rank, and CTR is context rather than an eligibility filter. Cannibalization candidate totals/shares are scoped to observed query/page rows rather than true query-level property totals; content-decay results compare only pages returned in both periods and do not turn one-sided row absence into zero traffic. |
 | **`indexing.list_pages`** / **`analytics.compare`** | Read | Analyze pages receiving Search Console impressions and compare two periods, optionally using the same search type and query/page/country/device/search-appearance filters for both periods. `analytics.compare` compares only dimension keys returned in both period responses; a key absent from one non-exhaustive Search Analytics response is not assumed to have zero metrics. Because its comparison contract includes average position, it excludes Discover and Google News. `indexing.list_pages` is performance data, not index coverage: a missing URL may still be indexed; use `urls.inspect` / `urls.inspect_many` for URL-level index status. |
@@ -105,9 +107,13 @@ Once connected, ask your assistant things like:
 - *"Which high-impression query/page rows have an average position between 5 and 15? Show me those optimization opportunities."*
 - *"Give me a weekly digest for `sc-domain:example.com` ending today."*
 - *"Do any of my sitemaps have errors or warnings?"*
-- *"Split my clicks into brand vs non-brand using a regex on the query."*
+- *"Using this brand regex I provide, approximate my clicks as brand vs non-brand."*
 - *"How is my site doing in Google Discover vs regular web search?"*
 
+Query regexes are a manual approximation only. Search Console's native Branded/Non-branded filter uses Google's own AI-assisted classification (including language variants, typos, and associated products/services), and that native classifier is not exposed as a Search Analytics API filter.
+
+Search Console also has dedicated Generative AI performance reports for Search and Discover. The current documented Search Analytics API does not expose a dedicated Generative AI search type or filter selector, so this MCP does not guess one. AI Overviews and AI Mode remain included in overall web Search performance data; use the Search Console UI for the dedicated Generative AI report until Google documents API access.
+
 ## Connect in your AI client
 
 Once you've deployed the server (see **[SETUP.md](SETUP.md)**), connect it by pasting your Worker's `/mcp` URL into your client:

package/SECURITY.md

@@ -58,7 +58,7 @@ delay and does not disclose another user's usage.
 | Category | Tools | Limit |
 |---|---|---|
 | Search Analytics | `analytics.query`, `insights.quick_wins`, `insights.cannibalization`, `insights.content_decay`, `indexing.list_pages`, `analytics.compare` | 30 per user / 10 minutes |
-| URL inspection | `urls.inspect`, `urls.inspect_many` | 20 inspected URLs per user / 24 hours; batch requests reserve one unit per URL |
+| URL inspection | `urls.inspect`, `urls.inspect_many` | 20 inspected URLs per user / 24 hours; batch requests reserve one unit per URL and run at most 3 inspections concurrently |
 | Search Console writes | `sites.add`, `sites.delete`, `sitemaps.submit`, `sitemaps.delete` | 10 per user / hour |
 | Indexing publish | `indexing.request` | 2 per user / 24 hours; 200 per deployment / 24 hours |
 | Weekly digest | `reports.weekly_digest` | 6 per user / hour |

package/SETUP.md

@@ -81,6 +81,7 @@ npx wrangler login
    - Replace `<your-worker>` with your Worker's name + subdomain. If you don't know it yet, deploy once (Step 6) to see the assigned `*.workers.dev` URL, then come back and add it here. The default Worker name is `mcp-gsc` (set in `wrangler.jsonc`).
    - The `http://localhost:8787/google/callback` entry is for local development with `npm run dev`.
    - The `http://127.0.0.1:8080/google/callback` entry is for the published `npx -y @digestseo/mcp-gsc` launcher, whose Registry transport is `http://127.0.0.1:8080/mcp` by default. If you set `PORT`, replace `8080` with that exact port.
+   - The `npx` launcher persists its local KV and Durable Object state in `~/.mcp-gsc/state` by default so npm package upgrades or cache cleanup do not discard the encrypted Google session. Set `MCP_GSC_STATE_DIR` to use another directory, and keep the same `TOKEN_ENCRYPTION_KEY` when reusing existing state. The first release with this stable path may require one Google reconnect because older launcher releases stored local state under the npm package cache.
    - The Worker derives Google's redirect URI from the MCP request URL. Google requires an exact authorized-URI match, so keep the same scheme, host, port, and `/google/callback` path. `localhost` and `127.0.0.1` are different hosts for this check.
    - The path must be exactly `/google/callback` — that's the route this server handles.
    - The DigestSEO-hosted instance also requires this exact callback URI in the OAuth client configured on its Worker: `https://mcp-gsc.digestseo.com/google/callback`.

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@digestseo/mcp-gsc",
-  "version": "0.4.11",
+  "version": "0.4.13",
   "private": false,
   "main": "scripts/glama-start.mjs",
   "bin": {

package/scripts/glama-start.mjs

@@ -1,5 +1,7 @@
 import { spawn } from 'node:child_process';
 import { createRequire } from 'node:module';
+import { homedir } from 'node:os';
+import { resolve } from 'node:path';
 import { fileURLToPath } from 'node:url';
 
 const port = process.env.PORT || '8080';
@@ -9,6 +11,9 @@ const googleRedirectUri = `${localBaseUrl}/google/callback`;
 const wranglerConfig = fileURLToPath(
   new URL('../wrangler.example.jsonc', import.meta.url),
 );
+const stateDir = process.env.MCP_GSC_STATE_DIR
+  ? resolve(process.env.MCP_GSC_STATE_DIR)
+  : resolve(homedir(), '.mcp-gsc', 'state');
 const forwardedVariables = [
   'GOOGLE_CLIENT_ID',
   'GOOGLE_CLIENT_SECRET',
@@ -20,6 +25,8 @@ const args = [
   'dev',
   '--config',
   wranglerConfig,
+  '--persist-to',
+  stateDir,
   '--local',
   '--ip',
   '127.0.0.1',
@@ -35,6 +42,7 @@ for (const name of forwardedVariables) {
 
 console.error(`[mcp-gsc] Local MCP endpoint: ${mcpUrl}`);
 console.error(`[mcp-gsc] Google OAuth redirect URI: ${googleRedirectUri}`);
+console.error(`[mcp-gsc] Local state directory: ${stateDir}`);
 
 const wranglerCli = createRequire(import.meta.url).resolve('wrangler');
 const child = spawn(process.execPath, [wranglerCli, ...args], { stdio: 'inherit' });

package/src/google.ts

@@ -309,6 +309,12 @@ export function assertSearchAnalyticsQueryCompatible(body: SearchAnalyticsQuery)
     throw new Error('Search Analytics dimensions must not contain duplicates.');
   }
 
+  if (body.dimensions.includes('searchAppearance') && body.dimensions.length > 1) {
+    throw new Error(
+      'Search Analytics searchAppearance must be the only grouping dimension. Discover an appearance value with dimensions ["searchAppearance"], then filter by that value in a separate query when grouping by page, query, country, device, date, or hour.',
+    );
+  }
+
   const hasHourDimension = body.dimensions.includes('hour');
   const usesHourlyData = body.dataState === 'hourly_all';
   if (hasHourDimension && !usesHourlyData) {
@@ -467,7 +473,9 @@ export interface UrlInspectionBatchResult {
   error?: string;
 }
 
-export async function inspectUrlsSequentially(
+export const URL_INSPECTION_BATCH_CONCURRENCY = 3;
+
+export async function inspectUrlsBoundedConcurrently(
   accessToken: string,
   siteUrl: string,
   inspectionUrls: readonly string[],
@@ -475,31 +483,53 @@ export async function inspectUrlsSequentially(
 ): Promise<UrlInspectionBatchResult[]> {
   const results: UrlInspectionBatchResult[] = [];
 
-  for (const inspectionUrl of inspectionUrls) {
-    try {
-      results.push({
-        inspectionUrl,
-        inspectionResult: await inspectUrl(
-          accessToken,
-          siteUrl,
-          inspectionUrl,
-          languageCode,
-        ),
-      });
-    } catch (error) {
-      if (error instanceof Error && error.message === GSC_ACCESS_REVOKED_MESSAGE) {
-        throw error;
-      }
-      results.push({
-        inspectionUrl,
-        error: error instanceof Error ? error.message : 'URL inspection failed.',
-      });
+  for (
+    let offset = 0;
+    offset < inspectionUrls.length;
+    offset += URL_INSPECTION_BATCH_CONCURRENCY
+  ) {
+    const chunk = inspectionUrls.slice(offset, offset + URL_INSPECTION_BATCH_CONCURRENCY);
+    const chunkResults = await Promise.all(
+      chunk.map(async (inspectionUrl): Promise<UrlInspectionBatchResult | Error> => {
+        try {
+          return {
+            inspectionUrl,
+            inspectionResult: await inspectUrl(
+              accessToken,
+              siteUrl,
+              inspectionUrl,
+              languageCode,
+            ),
+          };
+        } catch (error) {
+          if (error instanceof Error && error.message === GSC_ACCESS_REVOKED_MESSAGE) {
+            return error;
+          }
+          return {
+            inspectionUrl,
+            error: error instanceof Error ? error.message : 'URL inspection failed.',
+          };
+        }
+      }),
+    );
+
+    const accessRevoked = chunkResults.find((result): result is Error => result instanceof Error);
+    if (accessRevoked) {
+      throw accessRevoked;
     }
+    results.push(
+      ...chunkResults.filter(
+        (result): result is UrlInspectionBatchResult => !(result instanceof Error),
+      ),
+    );
   }
 
   return results;
 }
 
+// Kept for compatibility with callers that imported the original helper directly.
+export const inspectUrlsSequentially = inspectUrlsBoundedConcurrently;
+
 export interface SitemapEntry {
   path: string;
   lastSubmitted?: string | null;

package/src/index.ts

@@ -12,7 +12,8 @@ import {
   GSC_ACCESS_REVOKED_MESSAGE,
   MCP_RECONNECT_INSTRUCTION,
   inspectUrl,
-  inspectUrlsSequentially,
+  inspectUrlsBoundedConcurrently,
+  URL_INSPECTION_BATCH_CONCURRENCY,
   listSitemaps,
   listSites,
   getSite,
@@ -192,6 +193,12 @@ const CAPABILITIES_OUTPUT_SCHEMA = {
       description: z.string(),
     }),
   ),
+  provider_limits: z.object({
+    generative_ai_performance_report: z.object({
+      dedicated_api_supported: z.literal(false),
+      note: z.string(),
+    }),
+  }),
   hint: z.string(),
 };
 
@@ -242,6 +249,10 @@ const SEARCH_ANALYTICS_OUTPUT_SCHEMA = {
     'False because the Search Analytics API does not guarantee every data row; Google can return only top rows even after local pagination is exhausted.',
   ),
   provider_note: z.string(),
+  generative_ai_report_isolatable: z.literal(false).describe(
+    'False because the current documented Search Analytics API exposes no dedicated Generative AI report search type or filter selector.',
+  ),
+  generative_ai_note: z.string(),
   next_start_row: z.number().int().nonnegative().optional(),
   has_more: z.boolean(),
   truncated: z.boolean(),
@@ -479,6 +490,9 @@ function toolResponse<T extends Record<string, unknown>>(
 const SEARCH_ANALYTICS_PROVIDER_NOTE =
   'Google Search Analytics does not guarantee all data rows and can return only top rows. Local pagination fields describe what this server fetched or bounded; they do not prove provider-level exhaustiveness.';
 
+const GENERATIVE_AI_REPORT_API_NOTE =
+  "Search Console's dedicated Generative AI performance reports are not exposed by the current documented Search Analytics API as a dedicated search type or filter selector. AI Overviews and AI Mode remain included in overall web Search performance data. Do not infer isolated Generative AI metrics from analytics.query or guess a searchAppearance identifier.";
+
 function paginationMetadata(result: PaginatedSearchAnalyticsResult) {
   return {
     rows_fetched: result.rows.length,
@@ -569,7 +583,7 @@ const TOOL_CATALOG = [
   {
     name: 'analytics.query',
     description:
-      'Query Search Console search analytics (impressions, clicks, CTR, average position) over a date range, broken down by query, page, country, device, date, or search appearance. Supports filters and pagination. Google does not guarantee every data row and can return only top rows.',
+      'Query Search Console search analytics (impressions, clicks, CTR, average position) over a date range, broken down by query, page, country, device, date, or search appearance. Supports filters and pagination. Google does not guarantee every data row and can return only top rows. The current documented API does not expose a dedicated Generative AI performance-report selector; do not invent one.',
   },
   {
     name: 'insights.page_queries',
@@ -589,7 +603,7 @@ const TOOL_CATALOG = [
   {
     name: 'urls.inspect_many',
     description:
-      "Inspect Google's indexed versions of up to 10 URLs sequentially in one MCP call while charging the same URL Inspection safety budget per URL. This does not run live URL tests.",
+      `Inspect Google's indexed versions of up to 10 URLs with bounded concurrency of ${URL_INSPECTION_BATCH_CONCURRENCY} in one MCP call while charging the same URL Inspection safety budget per URL. This does not run live URL tests.`,
   },
   {
     name: 'sitemaps.list',
@@ -732,6 +746,12 @@ class GscMcpRuntime {
           access_mode: accessMode,
           auth_status: authStatus,
           tools: getToolCatalogForAccessMode(TOOL_CATALOG, accessMode),
+          provider_limits: {
+            generative_ai_performance_report: {
+              dedicated_api_supported: false as const,
+              note: GENERATIVE_AI_REPORT_API_NOTE,
+            },
+          },
           hint: "If auth_status is not 'connected', the user should reconnect this server in their MCP client to sign in with Google.",
         };
         return toolResponse(JSON.stringify(capabilities, null, 2), capabilities);
@@ -836,7 +856,7 @@ class GscMcpRuntime {
       'urls.inspect_many',
       {
         title: 'Inspect multiple URLs',
-        description: `Inspect the versions of up to 10 URLs currently known in Google's index from one Search Console property. This API does not run live URL tests. Google still processes one URL Inspection request per URL, so every requested URL consumes one quota unit and one unit of this server's shared URL-inspection safety budget. Requests are sent sequentially to avoid unnecessary bursts. Use this for a small group of important or debugging-target URLs; do not use it to crawl an entire site.`,
+        description: `Inspect the versions of up to 10 URLs currently known in Google's index from one Search Console property. This API does not run live URL tests. Google still processes one URL Inspection request per URL, so every requested URL consumes one quota unit and one unit of this server's shared URL-inspection safety budget. Requests use bounded concurrency of ${URL_INSPECTION_BATCH_CONCURRENCY}; results preserve input order, and a Google-access revocation stops later chunks from starting. Use this for a small group of important or debugging-target URLs; do not use it to crawl an entire site.`,
         inputSchema: {
           site_url: SEARCH_CONSOLE_PROPERTY_SCHEMA,
           inspection_urls: z
@@ -873,7 +893,7 @@ class GscMcpRuntime {
         if (rateLimitError) return rateLimitError;
 
         const accessToken = await this.getAccessToken(googleId);
-        const batchResults = await inspectUrlsSequentially(
+        const batchResults = await inspectUrlsBoundedConcurrently(
           accessToken,
           site_url,
           inspection_urls,
@@ -985,10 +1005,29 @@ class GscMcpRuntime {
           '  data_state to "hourly_all". The hourly date range can span at',
           '  most 10 inclusive days, and hourly data',
           '  is preliminary.',
+          '- SEARCH APPEARANCE uses a two-step workflow. To discover the',
+          '  property-specific appearance values Google currently exposes,',
+          '  call with dimensions: ["searchAppearance"] and no other grouping',
+          '  dimension. Then filter to one exact returned searchAppearance',
+          '  value in a separate query and group by page/query/country/device/',
+          '  date/hour as needed. Do not guess new appearance identifiers;',
+          '  discover the values Google returns for the property first.',
+          '- GENERATIVE AI REPORT: Search Console now has dedicated',
+          '  Generative AI performance reports in its UI, but the current',
+          '  documented Search Analytics API exposes no dedicated Generative',
+          '  AI search type or filter selector. AI Overviews and AI Mode remain',
+          '  included in overall web Search performance data. Do not guess a',
+          '  searchAppearance identifier or claim analytics.query isolates the',
+          '  dedicated Generative AI report.',
           '- Use dimension_filter_groups to filter by country, device, query',
           '  content, page URL, or search feature. includingRegex and',
-          '  excludingRegex use RE2 syntax. For brand vs non-brand splits,',
-          "  pass a single regex filter on the 'query' dimension.",
+          '  excludingRegex use RE2 syntax. A query regex can provide a manual',
+          '  brand/non-brand approximation when the caller supplies the brand',
+          "  pattern. It is not equivalent to Search Console's native Branded/",
+          '  Non-branded filter: Google describes that classification as',
+          '  AI-assisted (including language variants, typos, and associated',
+          '  products/services), and the Search Analytics API does not expose',
+          '  that native classifier as a filter.',
           "- data_state defaults to 'all' which matches the GSC dashboard.",
           "  Pass 'final' only when the user explicitly asks for stable,",
           '  non-preliminary data.',
@@ -1013,7 +1052,7 @@ class GscMcpRuntime {
             )
             .default(['query'])
             .describe(
-              "Dimensions to group rows by. Pass [] (empty array) to get a single row of true site-level totals. The 'hour' dimension requires data_state 'hourly_all' and an inclusive date range of at most 10 days. Google Discover and Google News do not support the query dimension.",
+              "Dimensions to group rows by. Pass [] (empty array) to get a single row of true site-level totals. searchAppearance must be the only grouping dimension; discover an appearance value with ['searchAppearance'], then filter to that value in a separate query when grouping by another dimension. The 'hour' dimension requires data_state 'hourly_all' and an inclusive date range of at most 10 days. Google Discover and Google News do not support the query dimension.",
             ),
           row_limit: z
             .number()
@@ -1041,7 +1080,7 @@ class GscMcpRuntime {
           search_type: z
             .enum(['web', 'image', 'video', 'news', 'discover', 'googleNews'])
             .default('web')
-            .describe('Which search index to query. Defaults to web. Google Discover and Google News do not support query grouping/filtering or average position.'),
+            .describe('Which documented Search Analytics search index to query. Defaults to web. Google Discover and Google News do not support query grouping/filtering or average position. The current API does not expose a dedicated Generative AI performance-report search type.'),
           aggregation_type: z
             .enum(['auto', 'byNewsShowcasePanel', 'byPage', 'byProperty'])
             .default('auto')
@@ -1135,6 +1174,8 @@ class GscMcpRuntime {
             : {}),
           provider_exhaustiveness_guaranteed: false,
           provider_note: SEARCH_ANALYTICS_PROVIDER_NOTE,
+          generative_ai_report_isolatable: false,
+          generative_ai_note: GENERATIVE_AI_REPORT_API_NOTE,
           has_more: bounded.resultPage.has_more,
           truncated: bounded.resultPage.truncated,
           byte_limit_reached: bounded.resultPage.byte_limit_reached,
@@ -1732,7 +1773,7 @@ class GscMcpRuntime {
             )
             .optional()
             .describe(
-              "Optional Search Console filters applied identically to both periods. Use query regex filters for brand/non-brand comparisons; countries use ISO 3166-1 alpha-3 codes.",
+              "Optional Search Console filters applied identically to both periods. A caller-supplied query regex can approximate a manual brand/non-brand split, but it is not equivalent to Search Console's AI-assisted native Branded/Non-branded filter, which the Search Analytics API does not expose. Countries use ISO 3166-1 alpha-3 codes.",
             ),
           limit: ANALYSIS_RESULT_LIMIT_SCHEMA,
           start_row: RESULT_START_ROW_SCHEMA,