Server Quality Checklist

Tool Scores

• catalog_releasesA
  4.4/5.0
  Behavior4/5

  Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

  No annotations exist, so the description bears full burden. It discloses the tool's core behavior (lists available versions and recommended version), the accepted version spec syntax, and the purpose of checking availability before doc_extract. It does not explicitly state read-only nature, but the verb '查看' (view) implies a non-mutating operation, and the description adds meaningful context beyond the simple name.

  Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

  Conciseness5/5

  Is the description appropriately sized, front-loaded, and free of redundancy?

  Three logically ordered sentences: what it does, accepted version spec formats, and when to use it relative to doc_extract. Every sentence is meaningful and no filler or redundancy exists.

  Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

  Completeness4/5

  Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

  For a single-parameter, read-like tool with no output schema, the description covers the core purpose, accepted input formats, and a critical usage ordering hint. It does not describe the return structure in detail, but the phrase '可用版本清单与推荐版本' gives a reasonable expectation. Overall sufficient for an agent to select and invoke correctly.

  Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

  Parameters3/5

  Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

  Schema coverage is 100%: the only parameter id is fully described in the schema as '条目规范 id（catalog_lookup 返回）' (canonical id from catalog_lookup). The description does not add further detail about the id parameter itself, only about the tool's overall behavior, so baseline 3 applies.

  Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

  Purpose5/5

  Does the description clearly state what the tool does and how it differs from similar tools?

  Description provides a specific action (view/list) and resource (available versions and recommended version for an entry). It clearly differentiates from sibling tools: catalog_lookup likely finds entries and doc_extract extracts docs, while this lists versions. The verb and object are unambiguous.

  Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

  Usage Guidelines5/5

  Does the description explain when to use this tool, when not to, or what alternatives exist?

  Explicitly states when to use this tool ('先于 doc_extract 调用' — call before doc_extract) to verify target version availability, and also explains supported version formats (latest, exact, prefix). This gives clear context for invocation relative to a sibling tool.

  Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

• doc_extractA
  4.4/5.0
  Behavior4/5

  Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

  With no annotations, the description carries full burden. It discloses relevance sorting, version selection logic (latest stable, exact/prefix), and that output includes releaseNote and source fields, providing meaningful behavioral context beyond the schema.

  Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

  Conciseness5/5

  Is the description appropriately sized, front-loaded, and free of redundancy?

  The description is three concise sentences covering purpose, focus usage, and version/return behavior. No redundancy, front-loaded with the main action, and every sentence adds useful information.

  Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

  Completeness4/5

  Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

  For a tool with 4 params, no output schema, and no annotations, the description explains core behavior, parameter nuances, and output fields (releaseNote, source). It is reasonably complete, though it could briefly note its relation to sibling catalog_lookup, but the schema already links id to catalog_lookup.

  Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

  Parameters4/5

  Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

  Schema descriptions cover 100% of parameters, so baseline is 3. The description adds value by explaining focus should be a single concept and version supports prefixes, enhancing what the schema labels only as 'focusing concept' and 'target version'.

  Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

  Purpose5/5

  Does the description clearly state what the tool does and how it differs from similar tools?

  The description clearly states it extracts document segments by entry id, version, and focus, returning them sorted by relevance score. This specific verb and resource distinguish it from siblings catalog_lookup and catalog_releases, which focus on catalog metadata and releases.

  Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

  Usage Guidelines4/5

  Does the description explain when to use this tool, when not to, or what alternatives exist?

  It gives practical guidance: focus should describe a single concept, with multiple calls for cross-concept questions, and explains version defaults and prefix support. While it doesn't explicitly name alternatives, the instructions are clear and actionable.

  Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

• catalog_lookupA
  4.5/5.0
  Behavior4/5

  Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

  With no annotations, the description carries the full burden of behavioral disclosure. It discloses that the tool returns a candidate list with relevance scores and hit signals, and details the scoring logic (name exact/prefix/alias hits > summary token hits > popularity adjustment). However, it does not fully define what 'hit signals' are, and omits potential edge behaviors such as no-match handling or request limits beyond the schema's limit parameter.

  Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

  Conciseness5/5

  Is the description appropriately sized, front-loaded, and free of redundancy?

  The description is concise and front-loaded with the primary action and results. It packs essential usage information (when to use, result ordering, scoring rationale) into two sentences without redundancy. Every sentence adds value, and the structure is clear.

  Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

  Completeness5/5

  Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

  For a search tool with 2 parameters, no output schema, and no annotations, the description is complete: it explains the search input, the output (candidate list with scores and hit signals), the ranking algorithm, and the workflow with doc_extract. The only minor gap is the exact definition of 'hit signals,' but that is not critical for using the tool correctly.

  Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

  Parameters3/5

  Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

  Schema description coverage is 100%, with both parameters (query and limit) already described in the input schema. The description adds no extra parameter semantics beyond what the schema provides; it merely restates that query can be a name or description, which is already in the schema. Therefore the baseline of 3 is appropriate.

  Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

  Purpose5/5

  Does the description clearly state what the tool does and how it differs from similar tools?

  The description clearly states the tool searches a documentation catalog by library/framework name or description, and returns candidate lists with relevance scores and hit signals. It explicitly distinguishes from sibling doc_extract by describing the intended workflow (use this first, then pass the returned id to doc_extract), and the resource is specific (documentation catalog).

  Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

  Usage Guidelines5/5

  Does the description explain when to use this tool, when not to, or what alternatives exist?

  The description provides explicit when-to-use guidance: '当不确定库的规范 id 时，先调用本工具' (call this tool when unsure of the canonical id), and names the alternative/next step: use the returned id to call doc_extract. It also explains the ranking order, which helps set expectations for result interpretation.

  Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.