Server Quality Checklist

Tool Scores

• get_paper_citationsA
  4.2/5.0
  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 it discloses a genuinely useful behavioral trait: '论文本身无引文数据时会返回业务错误' (returns a business error when the paper has no citation data). It also pins the output shape to search results via '字段同搜索结果'. It does not describe the error's structure or list ordering, but for a simple read-only list tool this is solid coverage.

  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 tight sentences: the first front-loads the core function and the cite_type selector, the second captures the important edge case. Every clause earns its place with no filler or repetition of schema content.

  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 fully documented schema, no output schema, and no annotations, the description covers the input requirement (paperid), the mode selection (cite_type), the output shape by reference to search results, and the error case. The main gap is that 'fields same as search results' assumes the agent already knows search_papers' return structure, and no detail is given on the business error's format.

  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 paperid, cite_type, and max_results all documented, so the baseline is 3. The description reinforces the cite_type modes (reference/citation) already present in the schema enum and adds the 'fields same as search results' output hint, but adds no materially new parameter-level meaning.

  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 states a specific verb and resource: '按 paperid 返回该论文的参考文献...或引证文献...列表' (return the reference/citation list by paperid). It clearly distinguishes itself from siblings search_papers (finding papers by query) and get_paper_detail (single-paper metadata) by centering on the citation relationship of a known paper.

  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 opening '按 paperid' establishes the key prerequisite: the caller already has a paper id, and the schema notes paperid comes from search_papers results, implying a follow-up workflow. The cite_type semantics (reference vs citation) are explicit, but the description never names alternatives or states when not to use this tool versus get_paper_detail.

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

• get_paper_detailA
  4.2/5.0
  Behavior4/5

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

  With no annotations, description carries burden. It fully discloses what the operation returns (full details, external links) and is clearly a read operation; no side effects or hidden behavior. Lacks notes on edge cases like missing paperid, but core behavior is transparent.

  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?

  One dense, structured sentence front-loads the verb and resource, enumerates all returned fields, then gives the paperid source. No filler, ideal length.

  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 tool with no output schema, the description provides the core semantics, return content list, and the paperid origin. It is sufficient for an agent to invoke it, though it does not describe result format or edge cases; sibling context rounds it out.

  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 covers paperid at 100%, so baseline 3 applies. Description restates the source of paperid ('来自 search_papers'), matching the schema, adding no new meaning beyond what the schema already provides.

  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 clearly states the tool returns complete paper details by paperid, enumerating specific fields (abstract, keywords, authors, journal, citations, DOI, etc.), and differentiates from search_papers and get_paper_citations by full-detail scope rather than search or citation-specific.

  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?

  States that paperid must come from search_papers results, giving clear context on how to invoke it. Doesn't explicitly contrast with get_paper_citations or state when not to use the tool, but the purpose itself implies it for full details.

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

• search_papersA
  4.2/5.0
  Behavior4/5

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

  With no annotations, the description carries the full burden. It discloses that the result is a candidate list, includes truncated abstracts, and requires the caller to choose the most matching paper—useful behavioral context. It does not mention any side effects or response structure details, but for a read-only search this is largely 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?

  The description is concise: two sentences, with the primary function and return fields front-loaded, followed by the workflow guidance. Every sentence contributes value and there is no redundancy.

  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 relatively simple search tool with full schema coverage and no output schema, the description provides the essential context: what the tool returns, the expected workflow, and the caller's responsibility to pick a match. The connection between paperid and get_paper_detail is implied but could be slightly more explicit.

  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. The description reinforces the query semantics (title/partial/keyword) but does not add meaningful detail about max_results or auto_detail_on_single beyond what the schema already provides.

  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 Baidu Academic by paper title (supporting partial titles/keywords) and returns a candidate list with a detailed set of fields. It also differentiates itself from the sibling get_paper_detail by describing the typical flow of first searching then fetching details.

  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 'typical flow' explicitly positions search_papers as the initial step before calling get_paper_detail, and instructs the caller to manually select the best match. However, it does not explicitly contrast with get_paper_citations or state when not to use the tool.

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