Server Quality Checklist

Tool Scores

• get_personA
  3.9/5.0
  Behavior4/5

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

  No annotations provided, so the description carries the full burden. It discloses that profiles are LLM-generated with draft review status, others' evaluations are verbatim from public editions and traceable, and appended historical evaluations. The database scope (pre-Qin to Han-Wei) is also stated. This provides good transparency about data quality and sourcing.

  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 concise (four sentences in Chinese) and front-loaded with the main function. Each sentence adds relevant detail (content types, source traceability, review status). No redundant 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?

  Given one parameter and no output schema, the description adequately outlines what the tool returns (profile, evaluations, events with sources). It also notes data quality and historical scope. The description is sufficient for an agent to understand the tool's output and limitations.

  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?

  The single parameter 'name' has a schema description listing examples and acceptable formats. The tool description does not add additional parameter semantics beyond what the schema already provides. Since schema coverage is 100%, a baseline score 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 states the tool retrieves person profiles, others' evaluations, and involved events with sources. It clearly specifies the verb '查' (query) and the resource (person). The tool name and description distinguish it from siblings like query_by_place (place query) and query_by_quality (quality query).

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

  Usage Guidelines3/5

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

  The description implies use for comprehensive person lookup but does not explicitly state when to use versus alternatives such as search_events (event-only) or query_by_quality. No prerequisites or exclusions are mentioned.

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

• query_by_qualityA
  4.3/5.0
  Behavior4/5

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

  No annotations are provided, so the description carries the transparency burden. It discloses that the mapping is judgment-based, not factual, and distinguishes auto_approved vs. draft review states. It also clarifies that evidence_quote is a true substring of the original text. Missing details like error handling or authorization, but the core behavioral traits are well covered.

  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 packs purpose, vocabulary, review states, and defaults without fluff. It is front-loaded with the main action and resource. Slightly long, but each clause carries meaningful 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?

  With no output schema, the description partially explains return content by mentioning evidence_quote and review statuses. It covers the key behavioral edge cases (draft filtering, controlled vocabulary). It does not fully specify the return structure or error behavior, but for a simple query tool with three parameters, it is adequately complete.

  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?

  The schema has 100% coverage, giving a baseline of 3. The description adds value by providing concrete examples of quality values (忠, 谋略, 勇, 仁, 残暴, 骄), explaining the controlled vocabulary and the review-state semantics for include_draft. This goes beyond the schema's parameter descriptions.

  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 queries by quality (Chinese: 品质) and returns representative events, people, and stories with original-text evidence. It explicitly enumerates the controlled vocabulary and distinguishes itself from siblings like search_events, get_person, and query_by_place by the query dimension (quality).

  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 it: when searching by a quality from a 55-term controlled vocabulary, using either Chinese or English slugs. It also specifies default behavior (only machine-approved outputs) and the include_draft option. It does not explicitly state exclusions vs. alternatives, but the context is clear enough.

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

• search_eventsA
  4.5/5.0
  Behavior5/5

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

  The description discloses that events are machine-merged and machine-reviewed, specifically noting that review_status is a batch machine approval, not per-item human review, and canonical_summary is an LLM-generated narrative. This is a valuable caveat beyond the basic operation, providing transparency about data reliability and provenance.

  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 two dense sentences that convey the purpose, the merging behavior, provenance formats, and reliability caveats. No filler or redundant information; every phrase adds value.

  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?

  There is no output schema, so the description appropriately explains the key return fields (review_status, canonical_summary) and the per-source provenance structure. It also covers the source roles, making the tool's behavior sufficiently predictable for an agent to select and invoke it.

  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?

  With 100% schema coverage, the baseline is 3. The description adds no extra meaning about parameter usage—it focuses on the result structure rather than how to filter the parameters. Thus it neither improves nor worsens the schema's already clear documentation.

  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: searching cross-book fused historical events with per-source provenance. It specifies the merging of records from multiple history books and the output structure, distinguishing it from sibling tools like get_person or query_by_place which target other entity types.

  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 establishes a clear context for when to use this tool—when you need an event synthesized from multiple historical sources. It does not explicitly name alternatives or exclusions, but its scope is sufficiently distinct that an agent can infer when to apply it.

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

• query_by_placeA
  4.9/5.0
  Behavior5/5

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

  Discloses key behaviors: uses multi-LLM consensus ('auto_approved'), returns a candidate list for disambiguation, does not auto-select, and avoids directional terms. With no annotations provided, the description fully carries the burden of transparency.

  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 a single focused paragraph. The first sentence immediately states the core purpose, followed by essential details and constraints. No extraneous wording.

  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 tool with 2 parameters, no output schema, and no annotations, the description covers all important aspects: purpose, input format, disambiguation behavior, exclusion criteria, and success logic. It leaves no significant gaps.

  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 baseline is 3. The description adds value by explaining how the 'place' parameter is resolved (disambiguation, accepted formats), which goes beyond the schema's single-line 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 purpose: using modern place names to lookup ancient stories and sources. It specifies the hierarchical levels supported (province/city/county) and distinguishes itself from siblings like get_person or query_by_quality by focusing on place-based queries.

  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?

  Explicit guidance on when to use (modern place name lookup), with examples ('西安', '陕西西安'). Clearly states what it does not do: it won't single-select ambiguous results and excludes directional terms like '江东'.

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