Server Quality Checklist

Tool Scores

• trailsearch_extractB
  3.3/5.0
  Behavior3/5

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

  With no annotations, the description carries the full burden of behavioral disclosure. It does add useful context: extracted content is 'clean,' include_raw_content returns 'raw (unfiltered)' content, and the return type is a JSON string. However, it does not disclose potential errors, rate limits, authentication needs, or what 'clean' means operationally.

  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 compact and well-structured, with the purpose front-loaded and params/returns organized clearly. There is little wasted text, though the endpoint name in the first sentence is minor redundancy given the tool name.

  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 description covers all parameters and states the return shape, and an output schema exists. But it lacks usage routing versus trailsearch_search, does not mention the default behavior of include_raw_content, and gives no constraints or caveats. Given the absence of annotations and low schema richness, these gaps are noticeable.

  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?

  Schema description coverage is 0%, so the description must compensate for the missing parameter explanations. It does, providing plain-language meaning for all three parameters: URLs to extract, an optional context query, and a raw-content flag. It could go further by noting that include_raw_content defaults to true and by clarifying how the query affects extraction.

  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 states a specific verb and resource: 'Fetch clean content from known URLs via the TrailSearch /extract endpoint.' It clearly identifies what the tool operates on, and the phrase 'known URLs' implicitly distinguishes it from trailsearch_search. However, it does not explicitly name the sibling or contrast the two, so it falls just short of full differentiation.

  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?

  There is no explicit guidance about when to use this tool versus trailsearch_search, and no mention of alternatives or exclusions. The phrase 'known URLs' weakly implies this tool is for URLs you already have rather than discovering them, but that is left to inference rather than stated.

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

• trailsearch_searchA
  4.3/5.0
  Behavior3/5

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

  With no annotations, the description carries the full burden of disclosing behavior. It mentions the return format (JSON string with results) and the input parameters, but it does not disclose potential side effects, rate limits, authentication requirements, or any underlying API constraints. While it is read-only in nature, this is not explicitly stated, and the description lacks depth on operational behaviors, leaving some ambiguity.

  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 well-structured: one sentence for the purpose, a clean list of arguments with short explanations, and a clear return statement. It avoids unnecessary fluff, front-loads the main action, and is easy to scan. No redundant information is present.

  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 the essential aspects: purpose, parameters, and return format. It mentions the output as a JSON string with specific fields (title, url, content/snippet, score), which is sufficient given that an output schema exists (though not shown). However, it does not address edge cases like error handling, pagination, or rate limits, and it does not mention the sibling tool or when to prefer this tool over it. These gaps prevent a perfect score but do not make the description inadequate for basic usage.

  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 provides only types and defaults with no descriptions (0% schema coverage). The description compensates by explaining each parameter in detail, such as 'query: search query string', 'mode: 'search' (fast, results only) or 'crawl' (also fetches page content)', and 'include_answer: request a short synthesized answer'. This adds significant meaning beyond the schema, fully covering all 9 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's purpose: 'Search the web through a self-hosted TrailSearch API' and mentions it is SearXNG-backed and Tavily-compatible. This distinguishes it from the sibling tool 'trailsearch_extract', which likely extracts content from a given URL, making the purpose 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?

  The description provides clear context on what the tool does and its parameters, but it does not explicitly compare it to the sibling tool 'trailsearch_extract'. It is implied that this tool is for web searching while the sibling is for extraction, but an explicit 'when to use this vs. that' statement is missing. This gives a clear context but lacks explicit exclusions, warranting a 4 rather than a 5.

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