Server Quality Checklist

Tool Scores

• web_searchA
  3.9/5.0
  Behavior4/5

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

  The description thoroughly discloses behavioral details: no API key needed, engine pool self-operated, at most two usable engines, back-fill on failures, relevance/quality ranking, deduplication, skipping unreachable or walled engines, and reporting an engine note. This exceeds the baseline and compensates for the absence of annotations. No contradiction with annotations since none are provided.

  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 and front-loaded with the primary purpose (search the web without API key) and then provides relevant behavioral details in a structured manner. Each sentence adds value; it is not overly verbose. Slight redundancy with the engines list in the title but overall 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?

  The description covers key aspects: purpose, engine selection, failure handling, result format, and edge cases (captcha/JS/bot walls). No output schema exists, but the description mentions what each result includes (title, URL, snippet, engine), which partially compensates. The absence of annotations is mitigated by the detailed description. Minor gaps remain about the return structure of the full response, but the information is sufficient for an agent to invoke the tool 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?

  The input schema already has complete (100% coverage) descriptions for all four parameters: count, query, engines, and maxSources. The description adds contextual insight on routing by query language and back-fill behavior but does not add substantial new parameter semantics beyond what the schema provides. Per the guideline, high schema coverage means 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 performs a web search using a self-operated engine pool, listing the supported engines and the result characteristics (title, URL, snippet, engine). It does not explicitly contrast with the sibling tool web_fetch, but the purpose is distinct and clear.

  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 how the engine pool is selected (query-language routing when no explicit pool), how failures are handled (back-filling, bounded attempts), and how results are ranked and deduplicated. It does not explicitly state 'when to use' versus 'when not to use' but provides contextual routing guidance. The sibling tool web_fetch is not referenced, so no alternative routing is mentioned.

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

• web_fetchA
  4.5/5.0
  Behavior5/5

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

  No annotations are provided, so the description carries full responsibility. It discloses anonymous access, no credentials, browser User-Agent, redirect limits, target blocking, and truncation behavior, which is strong transparency for a network 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?

  Three purposeful sentences: main behavior, safety boundaries, and output/usage context. No filler, no redundant schema echoing, and key constraints are front-loaded.

  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?

  With no output schema or annotations, the description still explains output format, status header components, redirects, target restrictions, and content conversion. This is an unusually complete one-paragraph contract for a fetch 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?

  The schema already clearly documents both parameters at 100% coverage, with maxChars including a default and limits. The description affirms bounded output but does not add substantial meaning about parameter formats 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 a specific verb, resource, and output: fetches one HTTP(S) URL and returns readable text. It also references web_search, making the distinction between search and fetch explicit without ambiguity.

  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?

  Description explicitly says to use it to read page content for a URL and gives a web_search output as an example, naming the sibling tool. It does not explicitly state when not to use it, so it stops short of a full when/when-not map.

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