@delta-infra/cli 1.1.19 → 1.1.21

package/skills/delta-protein/references/interpro_analyze.md

@@ -1,63 +1,63 @@
-# InterProScan Domain & Function Annotation (`huada_protein_tools` / `interpro_analyze`)
-
-This endpoint is a real endpoint of the `huada_protein_tools` tool. It can only be
-called via `delta-cli science invoke`; the business response described below lives
-under the CLI top-level `data` — read fields as documented in this file, do not
-recursively search. This file only documents the endpoint schema; it does not
-authorize direct HTTP. Endpoint names are authoritative as returned by
-`delta-cli science endpoints list huada_protein_tools`; use them verbatim — never
-guess, truncate, or alias.
-
-## Overview
-
-Annotate protein domains and functions with InterProScan.
-- Input: `protein_sequence` / `sequence_file` (FASTA/FA) / `structure_file` (PDB/CIF) — choose one; when `structure_file` is provided the backend extracts the sequence automatically
-- Optional: `chain` (protein chain identifier, default A)
-- Output: domain/family/GO summary `resultjson`, Excel (.xlsx) download link `download_url`
-
-## Invocation
-
-```text
-delta-cli science invoke --tool huada_protein_tools --endpoint interpro_analyze --data JSON
-```
-
-Required input groups (at least one per group; all groups must be satisfied):
-
-- `protein_sequence` / `sequence_file` / `structure_file`
-
-Request fields:
-
-| Field | Description | Default |
-|---|---|---|
-| `protein_sequence` |  | - |
-| `sequence_file` | FASTA/FA | - |
-| `structure_file` | PDB/CIF | - |
-| `chain` | Protein chain identifier, default A | A |
-
-## Response
-
-- CLI top-level envelope: a call succeeds only when the exit code is 0 AND `ok` is `true`; the service response lives under `data`.
-- Server-side contract: `status` (success/error/partial), `message`, `tool_type`, `resultjson`, `download_url`; some endpoints also return `total_count`. `resultjson` may be a single object or an array — read only the keys documented in this file, do not recursively search.
-- Binary/file artifacts (such as the PDB/XLSX/FASTA/ZIP files that `download_url` points to) are downloaded and verified with
-  `delta-cli science file download --tool huada_protein_tools --endpoint ... --output <path>`;
-  do not treat file contents as ordinary JSON results.
-
-## Output Projection
-
-> Verification status: derived from ToolSpec/agent templates; pending live calibration
-
-- Projection content: Domain, family, GO annotation summary + Excel (download_url)
-- Presentation form: Annotation summary text + Excel download link
-- Downstream reuse: -
-## Output Template
-
-- Title: **InterProScan domain and function annotation result**
-- Lead with the conclusion: key domain/family/GO annotation entries
-- Add the Excel detail file to the "Result files & downloads" section
-
-## Boundaries & Failure Modes
-
-- File-type parameters (`structure_file`/`sequence_file`/`msa_file` etc.) take server-accessible URL/path strings, not local upload paths; a `download_url` or `pdb_url` returned by an upstream endpoint can be backfilled directly as downstream input.
-- Make only the minimal calls needed to complete the task; `--data` carries only the fields declared by this endpoint. Do not invent enum values or branches beyond the required combinations.
-- Do not pass off local tool (RDKit/pymatgen/LAMMPS/self-attached MCP) results as this endpoint's results; do not connect directly to Huada or gateway URLs.
+# InterProScan Domain & Function Annotation (`huada_protein_tools` / `interpro_analyze`)
+
+This endpoint is a real endpoint of the `huada_protein_tools` tool. It can only be
+called via `delta-cli science invoke`; the business response described below lives
+under the CLI top-level `data` — read fields as documented in this file, do not
+recursively search. This file only documents the endpoint schema; it does not
+authorize direct HTTP. Endpoint names are authoritative as returned by
+`delta-cli science endpoints list huada_protein_tools`; use them verbatim — never
+guess, truncate, or alias.
+
+## Overview
+
+Annotate protein domains and functions with InterProScan.
+- Input: `protein_sequence` / `sequence_file` (FASTA/FA) / `structure_file` (PDB/CIF) — choose one; when `structure_file` is provided the backend extracts the sequence automatically
+- Optional: `chain` (protein chain identifier, default A)
+- Output: domain/family/GO summary `resultjson`, Excel (.xlsx) download link `download_url`
+
+## Invocation
+
+```text
+delta-cli science invoke --tool huada_protein_tools --endpoint interpro_analyze --data JSON
+```
+
+Required input groups (at least one per group; all groups must be satisfied):
+
+- `protein_sequence` / `sequence_file` / `structure_file`
+
+Request fields:
+
+| Field | Description | Default |
+|---|---|---|
+| `protein_sequence` |  | - |
+| `sequence_file` | FASTA/FA | - |
+| `structure_file` | PDB/CIF | - |
+| `chain` | Protein chain identifier, default A | A |
+
+## Response
+
+- CLI top-level envelope: a call succeeds only when the exit code is 0 AND `ok` is `true`; the service response lives under `data`.
+- Server-side contract: `status` (success/error/partial), `message`, `tool_type`, `resultjson`, `download_url`; some endpoints also return `total_count`. `resultjson` may be a single object or an array — read only the keys documented in this file, do not recursively search.
+- Binary/file artifacts (such as the PDB/XLSX/FASTA/ZIP files that `download_url` points to) are downloaded and verified with
+  `delta-cli science file download --tool huada_protein_tools --endpoint ... --output <path>`;
+  do not treat file contents as ordinary JSON results.
+
+## Output Projection
+
+> Verification status: derived from ToolSpec/agent templates; pending live calibration
+
+- Projection content: Domain, family, GO annotation summary + Excel (download_url)
+- Presentation form: Annotation summary text + Excel download link
+- Downstream reuse: -
+## Output Template
+
+- Title: **InterProScan domain and function annotation result**
+- Lead with the conclusion: key domain/family/GO annotation entries
+- Add the Excel detail file to the "Result files & downloads" section
+
+## Boundaries & Failure Modes
+
+- File-type parameters (`structure_file`/`sequence_file`/`msa_file` etc.) take server-accessible URL/path strings, not local upload paths; a `download_url` or `pdb_url` returned by an upstream endpoint can be backfilled directly as downstream input.
+- Make only the minimal calls needed to complete the task; `--data` carries only the fields declared by this endpoint. Do not invent enum values or branches beyond the required combinations.
+- Do not pass off local tool (RDKit/pymatgen/LAMMPS/self-attached MCP) results as this endpoint's results; do not connect directly to Huada or gateway URLs.
 - On failure, report a short summary of the CLI's raw error; do not blindly retry after remote computation timeouts (the outcome may be unknown because the task may already have happened).

package/skills/delta-protein/references/mpnn_design_sequence.md

@@ -1,71 +1,71 @@
-# MPNN Sequence Design (`huada_protein_tools` / `mpnn_design_sequence`)
-
-This endpoint is a real endpoint of the `huada_protein_tools` tool. It can only be
-called via `delta-cli science invoke`; the business response described below lives
-under the CLI top-level `data` — read fields as documented in this file, do not
-recursively search. This file only documents the endpoint schema; it does not
-authorize direct HTTP. Endpoint names are authoritative as returned by
-`delta-cli science endpoints list huada_protein_tools`; use them verbatim — never
-guess, truncate, or alias.
-
-## Overview
-
-Protein sequence design with the ProteinMPNN family of models.
-- Required: `structure_file` (.pdb/.cif)
-- Optional: `model_type` (protein_mpnn/ligand_mpnn/soluble_mpnn), `number` (1), `fixed_residues`, `redesigned_residues`, `chain`
-- Output: designed sequences with scores `resultjson`, `download_url`
-- Use case: when only a PDB/CIF structure file is provided
-
-## Invocation
-
-```text
-delta-cli science invoke --tool huada_protein_tools --endpoint mpnn_design_sequence --data JSON
-```
-
-Required input groups (at least one per group; all groups must be satisfied):
-
-- `structure_file`
-
-Server-side default parameters:
-
-- `model_type` = `protein_mpnn`
-- `number` = `1`
-
-Request fields:
-
-| Field | Description | Default |
-|---|---|---|
-| `structure_file` | PDB/CIF | - |
-| `model_type` | Model type, default protein_mpnn | protein_mpnn |
-| `number` | Number of sequences to generate, default 1 | 1 |
-| `fixed_residues` | Fixed residue positions, space-separated | - |
-| `redesigned_residues` | Positions to redesign only, space-separated | - |
-| `chain` | PDB chain identifier | - |
-
-## Response
-
-- CLI top-level envelope: a call succeeds only when the exit code is 0 AND `ok` is `true`; the service response lives under `data`.
-- Server-side contract: `status` (success/error/partial), `message`, `tool_type`, `resultjson`, `download_url`; some endpoints also return `total_count`. `resultjson` may be a single object or an array — read only the keys documented in this file, do not recursively search.
-- Binary/file artifacts (such as the PDB/XLSX/FASTA/ZIP files that `download_url` points to) are downloaded and verified with
-  `delta-cli science file download --tool huada_protein_tools --endpoint ... --output <path>`;
-  do not treat file contents as ordinary JSON results.
-
-## Output Projection
-
-> Verification status: derived from ToolSpec/agent templates; pending live calibration
-
-- Projection content: Number of designed sequences, scores/confidence, download_url
-- Presentation form: Text + download link
-- Downstream reuse: -
-## Output Template
-
-- Title: **MPNN sequence design result**
-- Lead with the conclusion: number of designed sequences and scores/confidence
-- Add the design-result file link to the "Result files & downloads" section
-
-## Boundaries & Failure Modes
-
-- File-type parameters (`structure_file`/`sequence_file`/`msa_file` etc.) take server-accessible URL/path strings, not local upload paths; a `download_url` or `pdb_url` returned by an upstream endpoint can be backfilled directly as downstream input.
-- Make only the minimal calls needed to complete the task; `--data` carries only the fields declared by this endpoint. Do not invent enum values or branches beyond the required combinations.
-- Do not pass off local tool (RDKit/pymatgen/LAMMPS/self-attached MCP) results as this endpoint's results; do not connect directly to Huada or gateway URLs.
+# MPNN Sequence Design (`huada_protein_tools` / `mpnn_design_sequence`)
+
+This endpoint is a real endpoint of the `huada_protein_tools` tool. It can only be
+called via `delta-cli science invoke`; the business response described below lives
+under the CLI top-level `data` — read fields as documented in this file, do not
+recursively search. This file only documents the endpoint schema; it does not
+authorize direct HTTP. Endpoint names are authoritative as returned by
+`delta-cli science endpoints list huada_protein_tools`; use them verbatim — never
+guess, truncate, or alias.
+
+## Overview
+
+Protein sequence design with the ProteinMPNN family of models.
+- Required: `structure_file` (.pdb/.cif)
+- Optional: `model_type` (protein_mpnn/ligand_mpnn/soluble_mpnn), `number` (1), `fixed_residues`, `redesigned_residues`, `chain`
+- Output: designed sequences with scores `resultjson`, `download_url`
+- Use case: when only a PDB/CIF structure file is provided
+
+## Invocation
+
+```text
+delta-cli science invoke --tool huada_protein_tools --endpoint mpnn_design_sequence --data JSON
+```
+
+Required input groups (at least one per group; all groups must be satisfied):
+
+- `structure_file`
+
+Server-side default parameters:
+
+- `model_type` = `protein_mpnn`
+- `number` = `1`
+
+Request fields:
+
+| Field | Description | Default |
+|---|---|---|
+| `structure_file` | PDB/CIF | - |
+| `model_type` | Model type, default protein_mpnn | protein_mpnn |
+| `number` | Number of sequences to generate, default 1 | 1 |
+| `fixed_residues` | Fixed residue positions, space-separated | - |
+| `redesigned_residues` | Positions to redesign only, space-separated | - |
+| `chain` | PDB chain identifier | - |
+
+## Response
+
+- CLI top-level envelope: a call succeeds only when the exit code is 0 AND `ok` is `true`; the service response lives under `data`.
+- Server-side contract: `status` (success/error/partial), `message`, `tool_type`, `resultjson`, `download_url`; some endpoints also return `total_count`. `resultjson` may be a single object or an array — read only the keys documented in this file, do not recursively search.
+- Binary/file artifacts (such as the PDB/XLSX/FASTA/ZIP files that `download_url` points to) are downloaded and verified with
+  `delta-cli science file download --tool huada_protein_tools --endpoint ... --output <path>`;
+  do not treat file contents as ordinary JSON results.
+
+## Output Projection
+
+> Verification status: derived from ToolSpec/agent templates; pending live calibration
+
+- Projection content: Number of designed sequences, scores/confidence, download_url
+- Presentation form: Text + download link
+- Downstream reuse: -
+## Output Template
+
+- Title: **MPNN sequence design result**
+- Lead with the conclusion: number of designed sequences and scores/confidence
+- Add the design-result file link to the "Result files & downloads" section
+
+## Boundaries & Failure Modes
+
+- File-type parameters (`structure_file`/`sequence_file`/`msa_file` etc.) take server-accessible URL/path strings, not local upload paths; a `download_url` or `pdb_url` returned by an upstream endpoint can be backfilled directly as downstream input.
+- Make only the minimal calls needed to complete the task; `--data` carries only the fields declared by this endpoint. Do not invent enum values or branches beyond the required combinations.
+- Do not pass off local tool (RDKit/pymatgen/LAMMPS/self-attached MCP) results as this endpoint's results; do not connect directly to Huada or gateway URLs.
 - On failure, report a short summary of the CLI's raw error; do not blindly retry after remote computation timeouts (the outcome may be unknown because the task may already have happened).

package/skills/delta-protein/references/multievolve.md

@@ -1,73 +1,73 @@
-# Multi-site Mutation Activity Prediction (`huada_protein_tools` / `multievolve`)
-
-This endpoint is a real endpoint of the `huada_protein_tools` tool. It can only be
-called via `delta-cli science invoke`; the business response described below lives
-under the CLI top-level `data` — read fields as documented in this file, do not
-recursively search. This file only documents the endpoint schema; it does not
-authorize direct HTTP. Endpoint names are authoritative as returned by
-`delta-cli science endpoints list huada_protein_tools`; use them verbatim — never
-guess, truncate, or alias.
-
-## Overview
-
-Predict the activity of multi-site combinatorial mutations with MultiEvolve.
-- Required: `training_dataset` (file with mutant and activity columns)
-- Optional: `mutant_pool`, `protein_sequence`/`sequence_file`/`structure_file`, `chain` (A), `topk` (5), `fix` (True)
-- Output: multi-site mutation activity scores `download_url`
-- Use case: predicting combinatorial mutation effects when training data is available; used when the user does not explicitly specify a mutation-site count
-
-## Invocation
-
-```text
-delta-cli science invoke --tool huada_protein_tools --endpoint multievolve --data JSON
-```
-
-Required input groups (at least one per group; all groups must be satisfied):
-
-- `training_dataset`
-
-Server-side default parameters:
-
-- `topk` = `5`
-- `fix` = `true`
-
-Request fields:
-
-| Field | Description | Default |
-|---|---|---|
-| `training_dataset` | CSV/XLSX with mutant/activity columns | - |
-| `mutant_pool` | CSV/XLSX mutant pool file, optional | - |
-| `protein_sequence` |  | - |
-| `sequence_file` | FASTA/FA | - |
-| `structure_file` | PDB/CIF | - |
-| `chain` | Protein chain identifier, default A | A |
-| `topk` | Number of results to return, default 5 | 5 |
-| `fix` | Whether to fix the random seed, default True | true |
-
-## Response
-
-- CLI top-level envelope: a call succeeds only when the exit code is 0 AND `ok` is `true`; the service response lives under `data`.
-- Server-side contract: `status` (success/error/partial), `message`, `tool_type`, `resultjson`, `download_url`; some endpoints also return `total_count`. `resultjson` may be a single object or an array — read only the keys documented in this file, do not recursively search.
-- Binary/file artifacts (such as the PDB/XLSX/FASTA/ZIP files that `download_url` points to) are downloaded and verified with
-  `delta-cli science file download --tool huada_protein_tools --endpoint ... --output <path>`;
-  do not treat file contents as ordinary JSON results.
-
-## Output Projection
-
-> Verification status: derived from ToolSpec/agent templates; pending live calibration
-
-- Projection content: Multi-site combinatorial mutation activity score topk (download_url)
-- Presentation form: Ranking text/table + download link
-- Downstream reuse: -
-## Output Template
-
-- Title: **Multi-site mutation activity prediction result**
-- Lead with the conclusion: recommended combinatorial mutations and activity-score trend (topk)
-- Add the full ranking to the "Result files & downloads" section
-
-## Boundaries & Failure Modes
-
-- File-type parameters (`structure_file`/`sequence_file`/`msa_file` etc.) take server-accessible URL/path strings, not local upload paths; a `download_url` or `pdb_url` returned by an upstream endpoint can be backfilled directly as downstream input.
-- Make only the minimal calls needed to complete the task; `--data` carries only the fields declared by this endpoint. Do not invent enum values or branches beyond the required combinations.
-- Do not pass off local tool (RDKit/pymatgen/LAMMPS/self-attached MCP) results as this endpoint's results; do not connect directly to Huada or gateway URLs.
+# Multi-site Mutation Activity Prediction (`huada_protein_tools` / `multievolve`)
+
+This endpoint is a real endpoint of the `huada_protein_tools` tool. It can only be
+called via `delta-cli science invoke`; the business response described below lives
+under the CLI top-level `data` — read fields as documented in this file, do not
+recursively search. This file only documents the endpoint schema; it does not
+authorize direct HTTP. Endpoint names are authoritative as returned by
+`delta-cli science endpoints list huada_protein_tools`; use them verbatim — never
+guess, truncate, or alias.
+
+## Overview
+
+Predict the activity of multi-site combinatorial mutations with MultiEvolve.
+- Required: `training_dataset` (file with mutant and activity columns)
+- Optional: `mutant_pool`, `protein_sequence`/`sequence_file`/`structure_file`, `chain` (A), `topk` (5), `fix` (True)
+- Output: multi-site mutation activity scores `download_url`
+- Use case: predicting combinatorial mutation effects when training data is available; used when the user does not explicitly specify a mutation-site count
+
+## Invocation
+
+```text
+delta-cli science invoke --tool huada_protein_tools --endpoint multievolve --data JSON
+```
+
+Required input groups (at least one per group; all groups must be satisfied):
+
+- `training_dataset`
+
+Server-side default parameters:
+
+- `topk` = `5`
+- `fix` = `true`
+
+Request fields:
+
+| Field | Description | Default |
+|---|---|---|
+| `training_dataset` | CSV/XLSX with mutant/activity columns | - |
+| `mutant_pool` | CSV/XLSX mutant pool file, optional | - |
+| `protein_sequence` |  | - |
+| `sequence_file` | FASTA/FA | - |
+| `structure_file` | PDB/CIF | - |
+| `chain` | Protein chain identifier, default A | A |
+| `topk` | Number of results to return, default 5 | 5 |
+| `fix` | Whether to fix the random seed, default True | true |
+
+## Response
+
+- CLI top-level envelope: a call succeeds only when the exit code is 0 AND `ok` is `true`; the service response lives under `data`.
+- Server-side contract: `status` (success/error/partial), `message`, `tool_type`, `resultjson`, `download_url`; some endpoints also return `total_count`. `resultjson` may be a single object or an array — read only the keys documented in this file, do not recursively search.
+- Binary/file artifacts (such as the PDB/XLSX/FASTA/ZIP files that `download_url` points to) are downloaded and verified with
+  `delta-cli science file download --tool huada_protein_tools --endpoint ... --output <path>`;
+  do not treat file contents as ordinary JSON results.
+
+## Output Projection
+
+> Verification status: derived from ToolSpec/agent templates; pending live calibration
+
+- Projection content: Multi-site combinatorial mutation activity score topk (download_url)
+- Presentation form: Ranking text/table + download link
+- Downstream reuse: -
+## Output Template
+
+- Title: **Multi-site mutation activity prediction result**
+- Lead with the conclusion: recommended combinatorial mutations and activity-score trend (topk)
+- Add the full ranking to the "Result files & downloads" section
+
+## Boundaries & Failure Modes
+
+- File-type parameters (`structure_file`/`sequence_file`/`msa_file` etc.) take server-accessible URL/path strings, not local upload paths; a `download_url` or `pdb_url` returned by an upstream endpoint can be backfilled directly as downstream input.
+- Make only the minimal calls needed to complete the task; `--data` carries only the fields declared by this endpoint. Do not invent enum values or branches beyond the required combinations.
+- Do not pass off local tool (RDKit/pymatgen/LAMMPS/self-attached MCP) results as this endpoint's results; do not connect directly to Huada or gateway URLs.
 - On failure, report a short summary of the CLI's raw error; do not blindly retry after remote computation timeouts (the outcome may be unknown because the task may already have happened).

package/skills/delta-protein/references/pisa_query.md

@@ -1,70 +1,70 @@
-# PISA Protein Interface Analysis (`huada_protein_tools` / `pisa_query`)
-
-This endpoint is a real endpoint of the `huada_protein_tools` tool. It can only be
-called via `delta-cli science invoke`; the business response described below lives
-under the CLI top-level `data` — read fields as documented in this file, do not
-recursively search. This file only documents the endpoint schema; it does not
-authorize direct HTTP. Endpoint names are authoritative as returned by
-`delta-cli science endpoints list huada_protein_tools`; use them verbatim — never
-guess, truncate, or alias.
-
-## Overview
-
-Query PDBePISA for protein interface analysis data.
-- Input (choose one):
-- `pdb_id`: PDB ID (e.g. 1B9E, 3WWJ, or the newer pdb_xxxxxxxx format)
-- `structure_file`: local/remote protein structure file path or URL (.pdb/.cif)
-- Processing path: `pdb_id` and `structure_file` both go through the PDBe new REST API (upload → submit → poll → filter p_value<0.5); plain HTTP, no browser
-- Output:
-- `resultjson`: {n_interfaces, interfaces[]} (filtered to p_value<0.5), each interface contains
-  interface_id / interface_area / solvation_energy / stabilization_energy /
-  p_value / n_interface_residues / n_hydrogen_bonds / n_salt_bridges /
-  n_other_bonds / residues (interface residues only, split across the two sides) / hydrogen_bonds / salt_bridges
-- `download_url`: download link for the full interface JSON (same structure as resultjson; residues keep details such as buried_surface_area)
-- Use case: analyze protein complex interface stability, identify key interface residues
-
-## Invocation
-
-```text
-delta-cli science invoke --tool huada_protein_tools --endpoint pisa_query --data JSON
-```
-
-Required input groups (at least one per group; all groups must be satisfied):
-
-- `pdb_id` / `structure_file`
-
-Request fields:
-
-| Field | Description | Default |
-|---|---|---|
-| `pdb_id` | PDB ID (e.g. 1B9E, 3WWJ or pdb_xxxxxxxx), mutually exclusive with structure_file | - |
-| `structure_file` | PDB/CIF | - |
-
-## Response
-
-- CLI top-level envelope: a call succeeds only when the exit code is 0 AND `ok` is `true`; the service response lives under `data`.
-- Server-side contract: `status` (success/error/partial), `message`, `tool_type`, `resultjson`, `download_url`; some endpoints also return `total_count`. `resultjson` may be a single object or an array — read only the keys documented in this file, do not recursively search.
-- Binary/file artifacts (such as the PDB/XLSX/FASTA/ZIP files that `download_url` points to) are downloaded and verified with
-  `delta-cli science file download --tool huada_protein_tools --endpoint ... --output <path>`;
-  do not treat file contents as ordinary JSON results.
-
-## Output Projection
-
-> Verification status: verified by a real `delta-cli` invocation
-
-- Projection content: n_interfaces and per interface: interface_id, interface_area, solvation_energy, stabilization_energy, p_value, hydrogen_bonds, salt_bridges, n_interface_residues, key interface residues
-- Presentation form: Interface summary text/table + full JSON download link
-- Downstream reuse: key interface residues can be used for interaction annotation
-## Output Template
-
-- Title: **PISA protein interface analysis result**
-- Lead with the conclusion: number of interfaces (n_interfaces) and stability (p_value/stabilization energy)
-- Per interface give interface_area, solvation/stabilization energy, p_value, hydrogen bond/salt bridge counts, n_interface_residues, key interface residues
-- Add the full interface JSON to the "Result files & downloads" section
-
-## Boundaries & Failure Modes
-
-- File-type parameters (`structure_file`/`sequence_file`/`msa_file` etc.) take server-accessible URL/path strings, not local upload paths; a `download_url` or `pdb_url` returned by an upstream endpoint can be backfilled directly as downstream input.
-- Make only the minimal calls needed to complete the task; `--data` carries only the fields declared by this endpoint. Do not invent enum values or branches beyond the required combinations.
-- Do not pass off local tool (RDKit/pymatgen/LAMMPS/self-attached MCP) results as this endpoint's results; do not connect directly to Huada or gateway URLs.
+# PISA Protein Interface Analysis (`huada_protein_tools` / `pisa_query`)
+
+This endpoint is a real endpoint of the `huada_protein_tools` tool. It can only be
+called via `delta-cli science invoke`; the business response described below lives
+under the CLI top-level `data` — read fields as documented in this file, do not
+recursively search. This file only documents the endpoint schema; it does not
+authorize direct HTTP. Endpoint names are authoritative as returned by
+`delta-cli science endpoints list huada_protein_tools`; use them verbatim — never
+guess, truncate, or alias.
+
+## Overview
+
+Query PDBePISA for protein interface analysis data.
+- Input (choose one):
+- `pdb_id`: PDB ID (e.g. 1B9E, 3WWJ, or the newer pdb_xxxxxxxx format)
+- `structure_file`: local/remote protein structure file path or URL (.pdb/.cif)
+- Processing path: `pdb_id` and `structure_file` both go through the PDBe new REST API (upload → submit → poll → filter p_value<0.5); plain HTTP, no browser
+- Output:
+- `resultjson`: {n_interfaces, interfaces[]} (filtered to p_value<0.5), each interface contains
+  interface_id / interface_area / solvation_energy / stabilization_energy /
+  p_value / n_interface_residues / n_hydrogen_bonds / n_salt_bridges /
+  n_other_bonds / residues (interface residues only, split across the two sides) / hydrogen_bonds / salt_bridges
+- `download_url`: download link for the full interface JSON (same structure as resultjson; residues keep details such as buried_surface_area)
+- Use case: analyze protein complex interface stability, identify key interface residues
+
+## Invocation
+
+```text
+delta-cli science invoke --tool huada_protein_tools --endpoint pisa_query --data JSON
+```
+
+Required input groups (at least one per group; all groups must be satisfied):
+
+- `pdb_id` / `structure_file`
+
+Request fields:
+
+| Field | Description | Default |
+|---|---|---|
+| `pdb_id` | PDB ID (e.g. 1B9E, 3WWJ or pdb_xxxxxxxx), mutually exclusive with structure_file | - |
+| `structure_file` | PDB/CIF | - |
+
+## Response
+
+- CLI top-level envelope: a call succeeds only when the exit code is 0 AND `ok` is `true`; the service response lives under `data`.
+- Server-side contract: `status` (success/error/partial), `message`, `tool_type`, `resultjson`, `download_url`; some endpoints also return `total_count`. `resultjson` may be a single object or an array — read only the keys documented in this file, do not recursively search.
+- Binary/file artifacts (such as the PDB/XLSX/FASTA/ZIP files that `download_url` points to) are downloaded and verified with
+  `delta-cli science file download --tool huada_protein_tools --endpoint ... --output <path>`;
+  do not treat file contents as ordinary JSON results.
+
+## Output Projection
+
+> Verification status: verified by a real `delta-cli` invocation
+
+- Projection content: n_interfaces and per interface: interface_id, interface_area, solvation_energy, stabilization_energy, p_value, hydrogen_bonds, salt_bridges, n_interface_residues, key interface residues
+- Presentation form: Interface summary text/table + full JSON download link
+- Downstream reuse: key interface residues can be used for interaction annotation
+## Output Template
+
+- Title: **PISA protein interface analysis result**
+- Lead with the conclusion: number of interfaces (n_interfaces) and stability (p_value/stabilization energy)
+- Per interface give interface_area, solvation/stabilization energy, p_value, hydrogen bond/salt bridge counts, n_interface_residues, key interface residues
+- Add the full interface JSON to the "Result files & downloads" section
+
+## Boundaries & Failure Modes
+
+- File-type parameters (`structure_file`/`sequence_file`/`msa_file` etc.) take server-accessible URL/path strings, not local upload paths; a `download_url` or `pdb_url` returned by an upstream endpoint can be backfilled directly as downstream input.
+- Make only the minimal calls needed to complete the task; `--data` carries only the fields declared by this endpoint. Do not invent enum values or branches beyond the required combinations.
+- Do not pass off local tool (RDKit/pymatgen/LAMMPS/self-attached MCP) results as this endpoint's results; do not connect directly to Huada or gateway URLs.
 - On failure, report a short summary of the CLI's raw error; do not blindly retry after remote computation timeouts (the outcome may be unknown because the task may already have happened).