Server Quality Checklist

Tool Scores

• list_documentsA
  3.5/5.0
  Behavior2/5

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

  No annotations provided, so description must cover behavioral traits. It states read-only listing but omits details like pagination, rate limits, or performance characteristics.

  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?

  Single sentence, front-loaded with verb and resource, no redundant words.

  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?

  Adequate for a parameterless tool with output schema; minor gaps like no mention of ordering, limits, or pagination.

  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?

  No parameters exist (0 params), so baseline is 4. Description adds value by listing output fields (doc_id, title, pages) which are not in the input schema.

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

  Purpose4/5

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

  Description specifies verb 'list', resource 'documents', and output fields. Clear purpose but does not distinguish from sibling tools like search or get_page.

  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?

  Implied usage is to get a list of all documents, but no explicit guidance on when to use versus alternatives or context for selection.

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

• get_citationA
  4.2/5.0
  Behavior3/5

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

  No annotations provided, so description carries full burden. States it provides citation text, implying read-only behavior, but does not explicitly disclose non-destructiveness, error conditions (e.g., invalid doc_id), or any limitations. Some behavioral context is present but not comprehensive.

  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 sentences plus an args line, front-loaded with the main explanation. No redundant words, every sentence earns its place. Efficient and well-structured.

  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 single-parameter tool with no output schema, description covers the key aspects: output types, usage instructions, and parameter source. Missing edge-case behavior (e.g., missing metadata) but overall fairly 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?

  With 0% schema description coverage, the description adds meaning for the doc_id parameter: 'document id from search/list_documents.' This links to sibling tools and clarifies where the ID comes from, going beyond the raw schema.

  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 it provides APA-7 citation (parenthetical, narrative, full reference) for a document, using verb 'get' and specific resource 'citation'. It distinguishes from siblings like list_documents and search by specifying the exact output format and context.

  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?

  Explicitly tells agent to use output verbatim and that the corpus is APA-only, never mix styles. Provides usage for direct quotes with page numbers. No alternative citation tool exists among siblings, so exclusion is not needed.

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

• searchA
  4.2/5.0
  Behavior4/5

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

  No annotations exist, so the description carries full burden. It transparently explains the HyDE fallback mechanism, how hypothesis is embedded and averaged, and how retrieved results are tagged. It also describes the note_type options. However, it does not mention any side effects, rate limits, or authorization needs.

  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 front-loaded with the main purpose, followed by a structured Args list. While slightly verbose, each sentence carries meaningful information. It could be more concise without losing clarity.

  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 5 parameters, complex HyDE behavior, and an existing output schema, the description covers search behavior comprehensively. It references sibling list_documents and explains return format. The only gap is not mentioning the output schema's actual structure, but it exists and is documented separately.

  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?

  Schema description coverage is 0%, yet the description adds rich meaning to all 5 parameters: query (natural-language question), top_k (number of results), doc_id (restrict to one document), note_type (exhaustive explanation of each value), hypothesis (HyDE fallback with details). This greatly exceeds what the schema 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 performs 'semantic search over the corpus' and returns 'chunks with page-level citations'. It is a specific verb+resource combination that distinguishes it from sibling tools like list_documents (lists documents) and get_page (retrieves a specific page).

  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 explains parameters and references sibling list_documents for doc_id, but does not explicitly state when to use this tool versus alternatives like get_page or render_page. No when-not-to-use guidance is provided.

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

• get_pageA
  4.3/5.0
  Behavior4/5

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

  The description indicates it is a read operation ('reading context') and explains the parameters, but with no annotations, it could be more explicit about being non-destructive or any limitations.

  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 extremely concise with two sentences and a bulleted list, front-loading the purpose and providing parameter details efficiently.

  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 is sufficient for a simple tool, explaining purpose and parameters, but could mention the return format explicitly since there is no output schema.

  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?

  With 0% schema description coverage, the description adds critical meaning: doc_id comes from search/list_documents and page is 1-based, fully compensating for the lack of schema property 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 it retrieves the full text of one page of a document for reading context around a search hit, distinguishing itself from siblings like search or render_page.

  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 after a search by referencing doc_id from search, but it does not explicitly specify when not to use it or mention alternatives like get_citation.

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

• render_pageA
  4.8/5.0
  Behavior4/5

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

  No annotations provided, so description carries full burden. Details highlight fallback logic and return content (image + report). Lacks potential side effects or performance notes, but still strong.

  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?

  Concise yet comprehensive. First sentence gives purpose, then context, then parameter details. No wasted words.

  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?

  Handles tool complexity well. Covers highlight logic, return value, and usage context. No output schema, but description provides enough detail.

  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?

  Schema coverage is 0%, but description adds full meaning: doc_id from search/list_documents, page is 1-based, highlight explains matching behavior and default. Great compensation.

  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?

  Clearly states 'Render a PDF page as an image, optionally with a passage highlighted.' Uses specific verb and resource, distinguishes from siblings like search/get_page.

  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 'Use after search/get_page to SHOW the user the exact source location.' Provides clear context and detailed highlight behavior.

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

• save_hydeA
  4.9/5.0
  Behavior5/5

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

  No annotations are provided, so the description carries full burden. It discloses idempotency per (doc_id, query), in-place updates, the non-citable nature, and searchability via note_type.

  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 well-structured with a clear lead sentence and a bullet-like list for arguments. It is slightly long but every sentence adds value; could be slightly more terse.

  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?

  Given no output schema and 0% schema coverage, the description fully explains inputs, idempotency, use case, and integration with other tools (searchable via note_type). It is complete.

  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?

  Schema coverage is 0%, so description must explain parameters. It thoroughly describes each parameter: query (user query and bridge id), hypothesis (answer paragraph), doc_id (optional scope), title (optional label derived from query).

  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 ('Persist') and resource ('HyDE hypothetical document'), and distinguishes this tool from siblings by specifying it's for hypothetical documents and creates a 'type=hyde bridge' for search.

  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 explicitly states when to use: after a 'search(query, hypothesis=...) fallback produced good grounding', and what not to use for: 'never a citable source'. It also mentions idempotency and searchability via note_type.

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