Server Quality Checklist

Tool Scores

• fetch_urlA
  3.7/5.0
  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 mention caching locally, content type handling, and optional saving to docs/<slug>.md with YAML frontmatter. However, it omits details about side effects like overwriting files, the meaning of 'refresh' and 'no_anubis', and potential rate limits or errors.

  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, front-loaded with the primary function, and every detail (content type handling, caching, saving) earns its place. It is efficient and well-structured without redundancy.

  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?

  Given no annotations, no output schema, and low schema coverage, the description should provide more operational context. It explains the core workflow and optional save, but lacks details on refresh behavior, the no_anubis flag, file overwrite semantics, and return format nuances. It is sufficient for basic use but has notable gaps for a moderately complex tool.

  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 only 17% (only 'url' has a description). The description partially compensates by mentioning the save feature (docs/<slug>.md) which relates to 'save', 'name', and 'subdir', but it does not explicitly explain these parameters or cover 'refresh' and 'no_anubis'. Thus, it adds some meaning but not enough to fully compensate for the undocumented parameters.

  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 fetches a single URL and returns clean markdown, with specific handling for HTML, JSON, and plain text. It distinguishes from siblings like web_search by focusing on direct URL fetching rather than searching.

  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 the tool is for fetching a specific URL when you have one, but it does not explicitly state when to use it over siblings or provide exclusion criteria. No alternatives are named, so usage guidance is only implied.

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

• list_docsA
  3.8/5.0
  Behavior4/5

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

  The description discloses three behavioral modes and states that path 'read the full body' of a doc. It does not mention effects of limit or subdir, but the read-only nature is implied. No annotations are provided, so this description carries the burden and mostly succeeds.

  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 two sentences, front-loaded with purpose and modes. The first sentence is dense but efficient; the second adds practical guidance. Every sentence earns its place, though the structure could be slightly clearer.

  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?

  Covers the core functionality and gives usage guidance, but lacks explanation for limit and subdir parameters, and does not position itself relative to search_docs. For a 4-param tool with no output schema and no annotations, this is a notable gap.

  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 0%. The description explains 'query' and 'path' parameters but omits 'limit' and 'subdir', leaving their semantics unresolved. It partially compensates for the missing schema documentation.

  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 browses and searches the local docs/ folder and enumerates three distinct modes (list all, keyword search, read by path). It differentiates from web tools with 'before going to the web', but does not explicitly distinguish it from the sibling search_docs.

  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 instructs to use this before going to the web, implying local docs should be checked first. However, it does not mention when not to use it or how it compares to sibling search_docs, leaving some ambiguity.

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

• web_searchA
  3.9/5.0
  Behavior3/5

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

  With no annotations provided, the description carries full burden. It discloses the backend (DuckDuckGo HTML), the cost structure (no API key, no per-query cost), and the return structure (list of title, url, snippet). However, it omits potential behavioral traits like rate limits, error handling, or behavior when no results are found. This is adequate but not rich.

  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, well-structured sentence that immediately states the tool's core value (free web search), backend, and return format, then ends with a useful pointer to fetch_url. Every word earns its place, making it highly efficient and easy to parse.

  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 search tool, the description covers the essential aspects: what it does, what it returns, and how to get full content. It lacks explicit guidance on when to prefer this over documentation search tools, but given the tool's simplicity and the pointer to fetch_url, it is mostly complete. A mention of result limit behavior would make it 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 schema describes 'query' but not 'limit', and the description adds no clarification for 'limit' behavior (e.g., number of results, default). It only indirectly implies that results are limited but without specifics. Since schema coverage is only 50%, the description should compensate for the undocumented 'limit' but fails to do so.

  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 is a 'web search' tool that 'Returns a list of {title, url, snippet}', identifying the specific verb (search), resource (web), and output format. It also differentiates from the sibling 'fetch_url' by explicitly directing users to pass URLs there for full content, firmly establishing its distinct role.

  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 usage: it's a free web search without API key or cost, implying it's for general web queries. It explicitly mentions 'Pass any URL to fetch_url for full content', offering a clear alternative for fetching full page content. However, it does not explicitly mention when to use 'lib_docs' or 'search_docs' instead, so exclusions are not fully stated.

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

• lib_docsA
  4/5.0
  Behavior4/5

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

  The description discloses key behavioral traits: the automatic fallback sequence across package registries and the optional side effect of saving to a file. Since no annotations are provided, this adds meaningful context beyond the schema, though it omits failure handling and return behavior.

  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 exceptionally concise at two sentences, with the main purpose stated first and supplementary details following. Every word contributes useful information; no redundant or vague language.

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

  Completeness2/5

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

  The description leaves significant gaps: there is no output schema, yet the return value (does it return content or just save to file?) is not explained. The `refresh`, `version`, and `ecosystem` parameters are completely undocumented, and the empty enum for ecosystem is confusing. The description covers only the basic use case.

  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 description adds value for the `name` parameter (format examples) and the `save` parameter (destination path), but schema coverage is low (20%) and the remaining parameters (refresh, version, ecosystem) are not explained in either schema or description. The description does not fully compensate for the coverage gap.

  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 'Fetch' and the resource 'README/docs for a library by name', with concrete examples like `react` and `owner/repo`. It differentiates itself from sibling tools (web_search, fetch_url, search_docs, list_docs) by focusing specifically on library documentation retrieval.

  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: use this tool when you need docs for a specific library, with automatic ecosystem detection. It does not explicitly state exclusions or alternative tools, but the intended usage is evident from the phrasing and examples.

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

• search_docsA
  4.1/5.0
  Behavior4/5

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

  No annotations are present, so the description carries the burden. It discloses the local-first search behavior, web fallback, bias toward official docs, and the effect of fetch_top=true. However, it does not mention potential side effects or explain the behavior of all parameters (e.g., save, target), which leaves some opacity.

  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, front-loaded with the core purpose, and includes only essential details (official docs, local-first, fetch_top). No filler or redundant statements.

  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?

  Given 6 parameters and no output schema, the description should explain return values and remaining parameters. It partially explains the difference between result list and markdown via fetch_top, but does not cover the behavior of local_only/skip_local/save or define the return structure sufficiently. Gaps remain for a complete understanding.

  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 only 17%, so the description must compensate. It does add semantic clarity for fetch_top and implies meaning for local behavior, but it does not explicitly explain local_only, skip_local, save, or target. The addition of fetch_top semantics is helpful but incomplete for such low schema coverage.

  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's a search tool for 'Language & API documentation' and differentiates itself from siblings by detailing a bias toward official docs and a local-first approach. The verb+resource 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 Guidelines4/5

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

  Provides clear context on when the tool is appropriate (language/API documentation lookups) and describes the local-first behavior with web fallback. It does not explicitly list exclusions or alternatives, but the context is strong enough to guide selection.

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