Server Quality Checklist

Tool Scores

• web_searchA
  3.8/5.0
  Behavior4/5

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

  With no annotations, the description carries the behavioral burden and fulfills it well: it discloses that the tool queries a live web source, returns ranked results with a defined shape, and supports a freshness filter. It does not cover rate limits or error behavior, but for a read-only search tool this is a minor gap.

  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 short sentences, each carrying distinct value, with the core action front-loaded. There is no redundant wording or filler.

  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 three-parameter search tool with full schema coverage, the description plus schema is sufficient to call it correctly. It lacks an explicit pointer to web_extract, but the output shape is stated and no output schema exists to contradict it.

  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%, so the schema already documents query, limit, and recency_minutes. The description only gestures at freshness filtering and ranked output, adding little meaning beyond the schema.

  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 action ('Search the live web') and resource, and it clarifies the return shape: ranked results with title, URL, and snippet. It does not explicitly contrast with sibling web_extract, but the search-vs-extract distinction is reasonably clear.

  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 phrase 'live web' implies the tool is for current, real-time information needs, and 'search' signals result discovery rather than page content extraction. However, there is no explicit when-to-use guidance or mention of web_extract as the alternative for reading page content.

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

• web_extractA
  4/5.0
  Behavior4/5

  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 usefully reveals that the tool renders JavaScript-heavy pages and produces clean Markdown, which are meaningful behavioral traits beyond the input schema. It does not mention error handling, redirects, or rate limits, but the core behavior of the tool is transparent enough.

  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 fluff. The main purpose and limit are front-loaded, followed by a valuable behavioral note about JavaScript rendering. Every clause 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 simple one-parameter tool with no output schema, the description conveys the essential information: what input is expected, what output is produced, and a key capability (JS rendering). The main gap is the lack of explicit guidance about when to use web_extract versus the web_search sibling.

  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 provides 100% coverage for the single 'urls' parameter with a clear description. The tool description adds context about output format and rendering behavior but does not add new meaning specific to the URL parameter beyond what the schema states.

  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 names a specific operation ('Fetch and extract'), a concrete output format ('clean Markdown content'), and a resource scope ('URLs'). It also distinguishes itself from the sibling tool web_search by focusing on fetching known URLs 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?

  Usage is implied through the contrast between web_extract and web_search, but no explicit guidance states when to choose this tool over the alternative. There are no exclusion criteria or conditions such as 'for search queries, use web_search instead'.

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