Server Quality Checklist

Tool Scores

• get_endpointB
  3.2/5.0
  Behavior2/5

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

  Annotations are completely absent, so the description carries the full burden. The description only says 'Get the full schema,' which is minimal. It does not disclose any behavioral traits such as output format nuances, potential error conditions, rate limiting, or what 'full schema' means. The schema exists but the description adds no behavioral context beyond the tool's basic action.

  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 sentence that is concise and front-loaded with the action. No extra fluff. However, given the tool's complexity and absent annotations, a bit more behavioral context could be added without much bloat, so it's not a 5.

  Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

  Completeness3/5

  Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

  The tool has an output schema, which likely conveys the return structure, so that part is covered. The parameters are well-documented in the schema. However, with no annotations and a minimal description, the agent lacks information on when to use this tool vs othersabbildung, the exact nature of the schema returned, and potential edge cases. For a tool that retrieves schemas, it is minimally adequate but not thorough.

  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 input schema already provides detailed descriptions for both parameters: 'slug' explains format and how to find it, 'summary' explains true/false behavior. Since schema coverage is 100%, the description adds little extra. The description itself mentions no parameter details, so it does not compensate beyond the schema, which is adequate.

  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?

  The description clearly states the verb and resource: 'Get the full schema for a UniFi API endpoint.' It distinguishes the tool from siblings by focusing on schema retrieval, though it doesn't explicitly name which sibling to use instead. The purpose is specific and unambiguous.

  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 usage: to get schemas for endpoints. It doesn't explicitly state when to use alternatives like list_endpoints or search_endpoints, but the parameter descriptions for 'slug' mention using those to find slugs, which gives some guidance. However, no explicit exclusions or alternative selection criteria beyond that.

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

• get_exampleB
  3.4/5.0
  Behavior3/5

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

  No annotations are provided, so the description carries the behavioral burden. 'Get' strongly implies a safe, read-only operation, and the output schema documents the return shape, so behavior is not opaque. However, the description does not explicitly confirm side-effect-free behavior or any other runtime characteristics in the absence of annotations.

  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, no filler, front-loaded with the action and resource. Every token in the available description is meaningful. There is no unnecessary framing or repeated 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?

  For a simple read-only example lookup with a fully documented input schema and an output schema present, the description plus structured fields give an agent enough to call the tool correctly. It could only be improved by adding sibling selection guidance, but that gap is already penalized under usage guidelines.

  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 schema itself documents all three parameters well, including defaults, formats, and allowed language values. The description adds nothing beyond that, which matches the baseline expectation for full schema coverage.

  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 states a specific verb and resource: 'Get a code example for a specific UniFi API endpoint.' It is clearly a retrieval tool, and 'code example' distinguishes it from response-sample or endpoint metadata tools. It does not explicitly name siblings, but the noun 'code example' narrows the purpose well.

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

  Usage Guidelines2/5

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

  The description gives no when-to-use or when-not-to-use guidance. With siblings such as get_endpoint, get_response_sample, and find_field, an agent is given no explicit help selecting this tool over alternatives. This is a real gap.

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

• get_response_sampleA
  3.5/5.0
  Behavior3/5

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

  No annotations are provided, so the description carries the burden. It discloses that the tool returns an example JSON response, which is a read-only behavior. However, it doesn't mention whether the response is static/sample data or a live call, nor any error behavior (e.g., unknown slug). The description is accurate but minimal.

  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 sentence, front-loaded with the core action and object. No wasted words. The example in the schema helps clarify the parameter format.

  Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

  Completeness3/5

  Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

  The tool is simple (1 param, output schema present), so the description is mostly sufficient. However, with no annotations and no mention of how to discover valid slugs (e.g., via list_endpoints), an agent might not know where to get the slug value. The output schema exists, so return format is covered, but the input source is not.

  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%: the 'slug' parameter is described as 'Endpoint identifier (e.g. 'listnetworks')'. The description adds the context that the slug identifies a specific endpoint, but doesn't add much beyond the schema. Baseline 3 is appropriate.

  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?

  The description clearly states the tool's purpose: retrieving an example JSON response for a specific UniFi API endpoint. It uses a specific verb ('Get') and resource ('example JSON response'), and the mention of 'specific UniFi API endpoint' distinguishes it from generic listing/searching tools. However, it doesn't explicitly differentiate from the sibling 'get_example', which may be a close alternative.

  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 usage: call this when you need an example response for a known endpoint identifier. It doesn't explicitly state when not to use it or name alternatives like 'get_example' or 'get_endpoint'. The context is clear enough for a simple tool, but lacks explicit routing guidance.

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

• get_endpoint_groupA
  3.6/5.0
  Behavior3/5

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

  With no annotations provided, the description must disclose behavioral aspects. It states that it returns a 'summary of every endpoint' and the purpose is to see all operations, which is a read operation. However, it does not mention any potential side effects or prerequisites (e.g., authentication) or limitations (e.g., pagination). There is no contradiction, but the description could add more behavioral details.

  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 brief two-sentence paragraph that front-loads the primary purpose in the first sentence and provides a clear explanation of the output in the second. It is concise with no unnecessary filler, earning a high score for efficiency.

  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 tool is simple with one parameter well-documented, an output schema present, and no nested objects. The description sufficiently explains the tool's purpose and output. However, it does not mention any limitations like pagination or rate limits, which could be relevant for a tool that returns a summary of many endpoints. This is a minor gap given the tool's simplicity.

  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 parameter is well-documented in the schema with examples. The description adds examples of resource names ('networks', 'firewall', 'wifi') and clarifies that it is a 'path fragment', which is slightly more than the schema. However, the added value is minimal given the schema already provides examples.

  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?

  The description clearly states the tool's function: 'Get all CRUD operations for a resource' with specific verb 'Get' and resource examples. It differentiates from siblings by focusing on grouping operations by resource path, while siblings like 'get_endpoint' retrieve individual endpoints. However, it could be more explicit about the distinction from '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?

  The description provides clear context for when to use this tool: when you need all operations for a specific resource. It gives examples of resource names and explains the benefit of seeing all available operations at once. It does not explicitly state when NOT to use it or mention alternatives, but the sibling names and purpose are clear enough.

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

• get_guideA
  3.8/5.0
  Behavior2/5

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

  No annotations are provided, so the description carries the full burden of behavioral disclosure. It only says 'Get a ... guide page,' which implies a read-only operation, but it does not address auth requirements, error behavior, rate limits, or what happens with invalid topics or slugs.

  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?

  A single, front-loaded sentence with no wasted words. The parenthetical examples are compact and informative, and the description is appropriately sized for a simple lookup tool.

  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 low-complexity tool with zero required parameters, 100% schema coverage, and an output schema, the description is mostly sufficient. It lacks explicit usage guidance versus sibling tools, but the resource type and examples cover the essential calling intent.

  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?

  Both parameters are already well-documented in the schema (app filter values, topic slug/search term, omit behavior), so the baseline is 3. The description adds useful examples of guide topics, which clarifies what kind of values 'topic' may take and pushes it slightly beyond the 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?

  States the exact resource ('UniFi API guide page') with a specific verb ('Get') and concrete examples (filtering syntax, error handling, getting started). This clearly distinguishes it from sibling tools that target endpoints, examples, or field schemas.

  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?

  No explicit when-to-use or alternative tool guidance is given. The topic examples imply it is for conceptual/API documentation rather than endpoint-specific details, but there is no exclusion or comparison to get_docs_info or list_endpoints, so the agent must infer when to choose this tool.

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

• list_endpointsA
  3.8/5.0
  Behavior3/5

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

  With no annotations, the description carries the full burden for behavioral disclosure. It states the tool lists all endpoints with method and path, implying a read-only operation, but does not disclose any additional traits such as pagination, ordering, or whether filters are case-sensitive. The simplicity of the operation makes this acceptable, but more could be said.

  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 sentence that immediately conveys the primary purpose and output. There is no redundant text or structural issues; it is highly concise and front-loaded.

  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 tool is simple with two optional parameters and an output schema that documents the return format. The description covers the essential information (what it lists and the output fields). Nothing critical is missing for an agent to call it correctly, though a note on read-only nature or explicit 'returns a list' could add slight completeness.

  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%, both 'app' and 'method' parameters are fully described in the schema. The description adds no additional meaning beyond what the schema already provides, so the baseline 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 clearly states the verb 'List' and the resource 'available UniFi API endpoints' with the specific output 'HTTP method and path'. This distinguishes it from siblings like search_endpoints (which implies searching) and get_endpoint (which implies a single endpoint retrieval).

  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 usage by mentioning optional filters, but it does not explicitly state when to use this tool versus alternatives, nor does it provide any exclusions or conditions. The context signals show siblings that might overlap, but the description lacks direct guidance on selection.

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

• find_fieldA
  4/5.0
  Behavior3/5

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

  The description discloses that the search covers request bodies, path parameters, and responses, including discriminator variants, and mentions it uses a pre-built index for speed. With no annotations provided, the description carries the burden, and it does add useful behavioral context, though it doesn't mention case-insensitivity (which is in the schema) or any limitations of the pre-built index.

  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 and front-loaded: the first sentence states the core purpose, and the second adds scope and performance context. Every sentence earns its place with no wasted 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?

  The tool has an output schema, so return values are already documented. The description covers the search scope and performance characteristics. It could mention what the output looks like or how to interpret results, but the output schema likely covers that. Overall, it's complete enough for an agent to call it correctly.

  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 schema already documents both parameters. The description adds context about what the search covers (request bodies, path parameters, responses, discriminator variants) but doesn't add meaning beyond the schema for the parameters themselves. Baseline 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's purpose: finding where a field appears across endpoint schemas. It specifies the resource (endpoint schemas) and the action (search), and distinguishes it from sibling tools like get_field_schema by focusing on cross-schema search rather than retrieving a single field's schema.

  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 implies when to use this tool: when you need to locate a field across request bodies, path parameters, and responses, including discriminator variants. It doesn't explicitly name alternatives or exclusions, but the scope is clear enough for an agent to select it over siblings like get_field_schema or search_endpoints.

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

• search_endpointsA
  4/5.0
  Behavior3/5

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

  With no annotations provided, the description carries the burden of behavioral disclosure. It does state that results are 'top matching' and 'ranked by relevance', which informs the agent that not all matches are returned. However, it does not mention whether the operation is read-only (implied by search but not explicit), error handling, pagination, or the number of results returned. This partial disclosure earns a mid-range score.

  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 sentences with no redundant phrases. The primary purpose is stated immediately, followed by a concise note on behavior and a directive for next steps. Every sentence earns its place; no fluff or unnecessary detail.

  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 the tool's moderate complexity (3 parameters, all documented in schema) and the existence of an output schema, the description covers the essentials: what it searches, what it returns (top matches), and how to proceed. It doesn't mention edge cases like empty results or result count limits, but these are minor for a search tool. The presence of an output schema reduces the need to explain return structures. Overall, it is sufficiently complete for an agent to call it correctly.

  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%, meaning every parameter (app, query, method) already has a description in the schema. The description adds little beyond what the schema provides; it merely implies that query can match name, path, or description, which is already implied by the parameter description. No additional semantic value is added, so the baseline 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 a specific verb (Search), a clear resource (UniFi API endpoints), and the search dimensions (name, path, method, description). It clearly distinguishes itself from sibling tools like list_endpoints (which likely lists all) and get_endpoint (which fetches one by slug) by framing this as a relevance-ranked 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 provides a clear workflow: search first, then use the returned slug with get_endpoint for full details. This implies when to use this tool (when you need to find an endpoint) and what to do next, but it doesn't explicitly contrast with list_endpoints or state conditions when search would be inappropriate. Some guidance is present but not exhaustive.

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

• get_docs_infoA
  4.3/5.0
  Behavior3/5

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

  With no annotations provided, the description carries the behavioral disclosure burden. 'Show' communicates a read-only, non-mutating operation, and listing what information is returned gives the agent a good sense of expected behavior. However, it does not explicitly state that it performs no side effects, requires no authentication, or has no significant cost; for such a simple metadata tool this is a minor gap rather than a serious one.

  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, front-loaded sentence that immediately states the tool's purpose and then lists the specific data elements. Every word adds value, with no filler or repetition.

  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 zero-parameter, read-only metadata tool with an output schema available, the description is complete. It tells the agent what the tool reports, and the presence of an output schema covers return-value details. No missing information would prevent correct invocation or interpretation.

  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, so the baseline is 4. The description correctly adds no parameter details because none exist, and the input schema confirms an empty object. Nothing more is needed.

  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 ('Show') and a clear resource ('which UniFi API docs are loaded'), then enumerates the exact content: API version, scrape date, endpoint and guide counts per app. This clearly differentiates it from sibling tools like list_endpoints or get_guide, which operate on individual docs rather than reporting loaded-doc metadata.

  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 clearly implies the use case: when an agent needs an overview of which documentation is loaded and its versioning/coverage stats, rather than querying individual endpoints or guides. It does not explicitly name alternatives or exclusions, but the zero-parameter metadata nature of the tool makes the appropriate context sufficiently clear.

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

• get_field_schemaA
  4.5/5.0
  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 does communicate that the tool returns only the requested schema subtree rather than a full endpoint schema, which is valuable. However, it does not explicitly disclose whether the operation is side-effect-free, what happens for invalid paths, or any auth/permission expectations, leaving some important behavioral gaps.

  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 compact and front-loaded: the core purpose is in the first sentence, the main alternative in the second, and the value intervention with find_field in the third. There is no filler or redundant restatement of the input schema.

  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?

  A simple read-only tool with two well-documented parameters, 100% schema coverage, and an output schema exists, so return-value details do not need repeating. The description covers why to use this tool, what to expect to receive (the subtree), and how to obtain valid field paths, making it functionally 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?

  Parameter description coverage is 100% and already includes good examples. The description adds extra meaning by explaining that slug points at an endpoint's schema and that field_path can be taken directly from find_field output, helping agents construct valid values.

  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 action ('drill into'), resource ('specific field's schema'), and context ('within an endpoint'). Explicitly contrasts with fetching the full endpoint schema and references find_field, giving agents enough to distinguish it from get_endpoint and other siblings.

  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?

  Gives an explicit when-to-use, saying to use this tool instead of fetching the full 70KB endpoint schema when only a subtree is needed. It also signals compatibility by stating that find_field paths work directly, which tells agents how this tool fits into a larger workflow.

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