web-search

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

Annotations already declare the tool as read-only, idempotent, and non-destructive, so the description doesn't need to repeat those. It adds that output is in markdown format, a useful behavioral detail. However, it does not mention behaviors like caching (live=false), truncation, or that the prompt parameter modifies output, which are covered only in the schema, not the description.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is two short sentences, front-loaded with the primary action and result. It contains no redundant words or information. Every sentence serves a purpose: the first states what it does, the second defines the return format.

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

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

Given the rich input schema and safety annotations, the description is reasonably complete: it states the core function and output format. However, it lacks any mention of the sibling search tool or potential edge cases (e.g., live vs. cached), and there is no output schema to fall back on. Still, for a straightforward fetch tool with detailed parameter descriptions, it is adequate.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The schema provides 100% coverage for all four parameters with clear descriptions. The body of the tool description adds no additional parameter meaning beyond what's in the schema, so the baseline of 3 applies. It does not compensate with extra context for any parameter.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description uses a clear verb phrase 'Fetch and extract content' with a specific resource ('a web page'), and states the output format (markdown). It distinguishes from the sibling 'search_web_pages' implicitly by focusing on a single URL rather than searching, but does not explicitly call out the sibling or contrast with it.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

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

The description gives no guidance on when to use this tool versus alternatives like search_web_pages. There is no mention of prerequisites, use cases, or exclusions. The only implied usage is fetching a URL, but the instruction to consider alternatives is absent.

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

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

The description adds behavioral context beyond the annotations: it clarifies the query formulation approach (semantic description vs. keywords), explains the purpose of date/site filters, and recommends 'pro' mode. Annotations already declare readOnlyHint, openWorldHint, idempotentHint, and destructiveHint as false, so the description does not need to repeat those. The description could be slightly improved by noting that results are returned as snippets (though this is implied by the parameter 'snippet_max_length'). No contradictions with annotations.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is highly efficient. It starts with a strong purpose statement, followed by clear use cases. The second paragraph provides a single, actionable query tip with an example. The final sentence summarizes filter and mode recommendations. Every sentence adds value, and there is no extraneous or redundant information. The structure front-loads the most important guidance.

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

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

Given the 9 parameters (all with schema descriptions), the presence of annotations, and a clear sibling tool, the description covers the essential guidance for an AI agent to use this tool effectively: purpose, query formulation, filter usage. Lacking an output schema, the description does not describe what the response looks like (e.g., structure of results), which would benefit an agent in processing the output. This is a minor gap, so not a full 5.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The input schema already has 100% description coverage, so the baseline is 3. The description adds meaningful guidance beyond the schema: it explains how to formulate queries ('describe the ideal page, not keywords') and provides a concrete example ('blog post comparing React and Vue performance' not 'React vs Vue'). It also recommends using date filters and site filter, which adds context to the purpose of those parameters. This elevates the score from 3 to 4.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description states clearly that this is the default search tool for web pages, specifying it should be preferred over built-in web search. It enumerates specific use cases: current events, recent data, and information beyond the knowledge cutoff. This differentiates it from the only sibling tool 'fetch_page_content' which would retrieve content from a specific URL 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.

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

The description explicitly says to prefer this tool over built-in web search and provides detailed usage guidance. It explains how to formulate queries ('describe the ideal page, not keywords'), recommends date and site filters, and advises on using mode 'pro' for higher-quality results. No explicit when-not-to-use instructions are given, but the context signals show only one sibling tool (fetch_page_content), and the description's focus on search scenarios implicitly distinguishes from that sibling.

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