cross-validated-search

Tool Scores

• browse_pageA
  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 full burden of behavioral disclosure, noting the 'pure text' extraction format which indicates HTML stripping. However, it omits safety classifications (read-only status), error handling behaviors for invalid URLs, or rate limiting details that would be necessary for complete 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 consists of exactly two efficiently structured sentences with zero redundancy—the first declaring functionality and the second establishing context. Every word serves the purpose of enabling correct tool selection.

  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 simple two-parameter schema with complete coverage and no output schema, the description adequately covers the essential purpose and workflow context. It appropriately omits return value details (which would be in an output schema) but could benefit from noting the truncation behavior when content exceeds max_chars.

  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 has 100% description coverage for both parameters ('url' and 'max_chars'), establishing a baseline score. The description implies the URL parameter usage but adds no additional semantic context about parameter formats, validation rules, or the truncation behavior implied by max_chars.

  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 specific verbs 'Fetch and extract' and identifies the resource as 'pure text content from a specific URL'. It explicitly distinguishes this tool from sibling 'search_web' by stating it reads 'the full content of a page found via search_web', clarifying the workflow relationship.

  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 second sentence provides explicit usage context by naming the sibling tool 'search_web' and establishing this as the follow-up step to read discovered pages. While it clearly indicates when to use the tool, it lacks explicit guidance on when not to use it or alternative approaches.

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

• search_webA
  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 full disclosure burden. It adds valuable behavioral context by specifying 'real-time' information, indicating result freshness. However, it omits details about result limits, output format, or rate-limiting that would help an agent understand resource constraints.

  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 well-structured sentences with zero waste. The first sentence front-loads capability (what it searches for), and the second provides usage guidance (when to use it). Every word earns its place.

  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 search tool with no output schema, the description adequately covers the primary use case (fact verification) and content types. The 100% schema parameter coverage compensates for missing output details, though a brief note about result sets would strengthen completeness given the lack of annotations.

  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%, establishing a baseline of 3. The description adds semantic value by mentioning 'news, images, books, or videos' which maps to the 'type' parameter enum values, helping agents understand the parameter's purpose beyond the schema's 'Type of search' label.

  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 the specific verb 'Search' with the resource 'the web' and enumerates the content scope (news, images, books, videos). It clearly distinguishes from the sibling 'browse_page' by emphasizing broad search vs. page-specific browsing.

  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 phrase 'Always use this to verify facts or get up-to-date information before answering' provides strong prescriptive guidance on when to invoke the tool. However, it stops short of explicitly contrasting with the sibling 'browse_page' or stating when not to use this tool.

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