Server Quality Checklist

Tool Scores

• get-spec-overviewA
  4/5.0
  Behavior3/5

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

  With no annotations, the description carries the burden. It states it reads the document (implying read-only) but does not disclose potential side effects like network access, caching, or error behavior. However, it does mention the default-document fallback, adding some transparency 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?

  Two concise sentences, front-loaded with the action and output, then parameter details. No wasted words; it efficiently conveys purpose, usage context, and parameter behavior.

  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 simple tool with one optional parameter and no output schema, the description is fairly complete. It specifies what the overview includes and the fallback behavior. It could mention error handling or that it does not return the full spec, but that is not essential given the sibling context.

  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% and the description essentially repeats the schema's parameter info without adding new meaning. The baseline for high coverage is 3, and since the description adds no extra semantics beyond the schema, a 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 reads Swagger/OpenAPI documents and returns overview information (info, servers, tags stats, total endpoints). It explicitly frames it as the first step before using other tools, distinguishing it from siblings like get-api-detail or get-openapi-spec.

  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?

  The description provides clear usage context ('usually this is the first step before using other tools') and explains the optional source parameter falls back to a default document. It does not explicitly name alternates or when not to use it, but the context strongly implies its role.

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

• get-api-detailA
  4.1/5.0
  Behavior4/5

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

  With no annotations provided, the description carries the full burden and delivers: it discloses the non-obvious behaviors of recursive $ref expansion and circular-reference marking ($ref-cycle), which go beyond what annotations or schema could convey. It doesn't cover error cases or auth, but for a read-only detail fetch, this is solid behavioral disclosure.

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

  Conciseness4/5

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

  The description is a compact paragraph with a front-loaded purpose statement followed by parameter clarifications, earning its space. The odd 'source 同上' (same as above) reference is confusing without external context, slightly marring an otherwise efficient structure.

  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 3-parameter tool with no output schema and no annotations, the description covers the essential ground: return contents, expansion behavior, cycle handling, and exact-match requirements. While it could note error behavior for non-existent paths, and the lack of annotations in the context, the description is adequate for an agent to invoke this tool effectively.

  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%, so the baseline is 3 with the schema doing the heavy lifting. The description restates the parameters in prose and adds the 'path must exactly match' caveat, but this mirrors the schema text. The description's value-add lies in return semantics rather than parameter meaning, so no score above baseline is warranted.

  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 uses a specific verb+resource structure ('按 method + path 返回接口完整详情' - returns complete API details by method + path), enumerating return contents (parameters, request body, response structure) and explicitly noting the recursive $ref expansion behavior. This $ref-cycle detail meaningfully distinguishes it from siblings like get-openapi-spec and search-apis.

  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?

  The description gives practical usage context by noting the path must exactly match and directing users to query with search-apis first ('可先用 search-apis 查询'). It provides clear context for the workflow, though it lacks explicit exclusions or direct comparison against get-spec-overview/get-openapi-spec siblings.

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

• search-apisA
  4.1/5.0
  Behavior4/5

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

  With no annotations, the description carries the burden. It discloses the matching fields, case-insensitivity, return fields (method/path/summary/tags), behavior when keyword is omitted (returns all), and limit constraints. This is ample transparency for a read-only search tool.

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

  Conciseness4/5

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

  The description is a single dense sentence that front-loads the purpose and integrates parameter notes. It is efficient and avoids unnecessary words, though the inline parameter list could be slightly clearer as separate points.

  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?

  The description covers the search behavior, return list fields, and a clear next step (get-api-detail). No output schema exists, so the return fields are stated. It lacks error-handling or pagination details, but for a moderate-complexity search tool, these are not critical.

  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% with descriptions for all three parameters. The description restates the parameter meanings (e.g., keyword, limit) but does not introduce new semantic details beyond what the schema already provides, such as syntax or interaction between parameters.

  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 APIs by keyword, specifying the exact fields being matched (path, summary, description, tags, operationId). It distinguishes itself from get-api-detail by directing users there after finding the exact path, which shows a specific search-and-then-detail workflow.

  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?

  The description provides clear context: use this tool to search by keyword and then follow up with get-api-detail. It doesn't explicitly compare with get-spec-overview or get-openapi-spec, but the purpose is implicit enough that a user can infer when to use it.

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

• refresh-cacheA
  4.5/5.0
  Behavior4/5

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

  With no annotations provided, the description carries the full burden. It discloses important behaviors: failure retains old cache, and refreshing all cached sources excludes the default if it was never loaded. It does not mention authentication or rate limits, but covers key side effects.

  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 yet comprehensive, covering behavior, parameter handling, and failure cases without unnecessary fluff. It is well-structured with clear conditional logic.

  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?

  The description covers all essential aspects of the tool's operation: parameter semantics, edge cases, and failure behavior. It does not describe return values, but since no output schema is provided, this is not a significant gap. Overall, it is complete for the given complexity.

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

  Parameters5/5

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

  The description adds substantial meaning beyond the schema. It clarifies that 'source' is optional and explains the exact consequences of providing or omitting it, including the nuance about the default document not being refreshed unless previously loaded. This goes beyond the basic schema description.

  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's function: forcibly reloading document sources and replacing the cache immediately. It distinguishes itself from sibling tools (get-spec-overview, search-apis, etc.) by focusing on cache refresh rather than retrieval or search.

  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?

  The description explains when to use the tool (to refresh cache) and details the behavior of the optional 'source' parameter, including the difference between refreshing a specific source versus all cached sources. It does not explicitly contrast with sibling tools but implies the use case clearly.

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

• get-openapi-specA
  4.7/5.0
  Behavior4/5

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

  With no annotations, the description discloses key behavior like auto-truncation ('超长自动截断') and default parameter values. It does not mention permissions or side effects, but for a read-only export this is sufficient.

  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 sentences pack purpose, parameter list, and usage advice without wasted words. The structure is logical and front-loaded.

  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?

  Covers all essential aspects: output format, segmentation, truncation, defaults, and usage guidance. Return values are implied by '文档文本' and no output schema is needed.

  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 coverage is 100%, so the baseline is 3. The description adds value by summarizing parameter defaults and explicitly linking max_length to truncation behavior, though 'source 同上' is vague.

  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 exports full or segmented OpenAPI 3.x document text, with a specific verb and resource. It distinguishes itself from sibling tools by suggesting overview/search/detail tools for other needs.

  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 advises when to use the section parameter for large documents and directs users to alternative tools (概览/搜索/详情), providing clear when-to-use and when-not-to-use guidance.

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