Server Quality Checklist

Tool Scores

• get_exampleA
  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 disclosure burden. It reveals two key behaviors: version-agnostic matching and fallback to the 'returns: line'. It does not mention auth or rate limits, but for a read-only retrieval tool, this is adequate.

  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, each with a clear role: purpose, version behavior, failure mode. No redundancy or fluff. Excellent front-loading.

  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?

  The output schema is present (not shown), so return values need not be described. The description covers the primary function, edge cases, and key behavioral nuances. Given low complexity, it is fully complete.

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

  Parameters2/5

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

  The only parameter 'path' has 0% schema description coverage. The description references 'endpoint path' but does not specify format, examples, or constraints beyond the property name. Adding semantics like 'expected format: /api/v2/x' would improve clarity.

  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 'Return a real captured example response body for an endpoint path,' specifying the verb and resource. It distinguishes from siblings by focusing on example retrieval rather than endpoint metadata or documentation 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 the version-agnostic slug fallback and the fallback behavior when no example is captured, guiding the agent on expected outcomes. It does not explicitly contrast with siblings but provides context for when the tool succeeds or fails.

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

• get_playbookA
  4.3/5.0
  Behavior3/5

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

  No annotations are provided, so the description carries the full burden. It mentions coverage of authentication and error semantics but does not explicitly state that the tool is read-only, non-destructive, or clarify side effects. More explicit disclosure of behavioral traits would improve 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 concise: a single sentence defining the main purpose, followed by a list of content areas. It is front-loaded and efficient, with no redundant or unnecessary information.

  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 zero parameters, no annotations, but an existing output schema, the description provides comprehensive context about the tool's return value and its scope. It covers all necessary aspects for a zero-input tool, making it 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 tool has zero parameters and 100% schema description coverage. The description adds value by explaining what the tool returns (usage rules), which goes beyond the schema. Baseline for no parameters is 4, and this is justified.

  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 that the tool returns the global DivineAPI usage rules (the docs-pack header), listing specific content areas. This distinguishes it from siblings like get_endpoint or search_docs, which likely focus on individual endpoints 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 explicitly advises 'Read this before constructing any request,' providing strong usage guidance. While it does not explicitly list when not to use or compare to alternatives, the imperative is clear and contextually sufficient.

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

• search_docsA
  4.4/5.0
  Behavior4/5

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

  Describes case-insensitive token scan, ranking by match count, and return of entire cards with specific fields. No contradictions, and covers behavior beyond 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?

  Front-loaded purpose, efficient sentences, no fluff. Every sentence adds value: purpose, algorithm, usage guidance.

  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 output schema and sibling tools, description is complete: explains return format, ranking, and usage. Lacks pagination info but acceptable for search tool.

  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 schema coverage at 0%, description compensates by explaining `query` as keyword and `limit` as 'up to limit whole cards,' adding meaning beyond basic 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?

  Clearly states verb (search), resource (docs), and outcome (return matching endpoint cards). Distinguishes from siblings like get_endpoint and list_endpoints.

  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?

  Provides explicit when-to-use guidance: 'when you know roughly what you want but not the exact path.' While no direct alternatives are named, sibling tools imply alternatives.

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

• list_endpointsA
  4.5/5.0
  Behavior4/5

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

  No annotations provided, so description carries full burden. It discloses output format ('path [host]' lines) and case-insensitive filtering. Lacks explanation of error handling or rate limits, but adequate for a simple listing tool.

  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, front-loaded with main purpose. No extraneous information. Every word contributes.

  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?

  Has output schema so return values need not be detailed. Description covers listing and filtering. Lacks mention of pagination or limits, but tool is likely simple enough. Adequate.

  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?

  Input schema has no description for parameter 'category' (0% coverage). Description adds essential semantics: case-insensitive substring filter with concrete examples ('Indian', 'Western', etc.), greatly aiding correct parameter use.

  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 verb 'List', resource 'endpoint paths with hosts', and filter capability. It distinguishes from siblings like get_endpoint which retrieves a single endpoint.

  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?

  Provides clear context: use without argument for full list, or with category substring for filtered list. Examples given. Could explicitly contrast with siblings but implication is clear.

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

• get_endpointA
  4.8/5.0
  Behavior5/5

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

  The description fully discloses behavior: exact match returns card, substring match returns closest endpoint, no match returns did-you-mean list. It also details the card's contents (host, summary, params, response fields). No annotations are provided, but the description covers all relevant behavioral traits.

  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 at four sentences, front-loaded with the main purpose, then providing examples and behavior details. Every sentence adds value without redundancy.

  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 the tool's simplicity (one parameter) and the presence of an output schema (not shown but noted), the description fully covers input behavior, matching logic, and output contents. It is complete enough for an agent to understand and invoke the tool correctly.

  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 input schema has one parameter 'path' with no description (0% coverage). The description adds crucial meaning: provides an example path, explains how the path is matched, and clarifies the behavior for exact vs. approximate matches. This fully compensates for the schema's lack of detail.

  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 returns a full reference card for an endpoint path, with specific verb 'Return' and resource 'reference card'. It distinguishes from siblings like get_example (examples) and list_endpoints (listing) by focusing on a single endpoint's card.

  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 for when to use the tool: when you need a reference card for a specific endpoint path. It explains input expectations (exact path) but does not explicitly mention when not to use or list alternatives among siblings.

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