web-search

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

Annotations already declare readOnlyHint, idempotentHint, openWorldHint, and destructiveHint=false, covering the safety profile. The description adds the markdown output format, which is useful, but says nothing about live-fetch caching, truncation, or the LLM-extraction path described in the schema.

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?

Two sentences, zero waste, with the core action front-loaded before the return format. Nothing extraneous.

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?

With rich annotations, a fully documented 6-parameter schema, and no output schema, the definition covers what an agent needs to invoke it. The one gap is not routing between this tool and its sibling search_web_pages.

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?

Schema description coverage is 100%, so every parameter is already documented with examples, defaults, and constraints. The description adds no parameter-level information beyond the schema, so the baseline of 3 applies.

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?

States a specific verb and resource: 'Fetch and extract content from a web page,' and adds the return format (markdown). It is clearly distinguishable from the sibling search_web_pages by the fetch-vs-search verb, though it never names the sibling explicitly.

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?

Usage is implied -- fetch when you have a URL -- but the description gives no explicit when-to-use guidance, no condition that selects it over search_web_pages, and no prerequisite or caveat language.

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?

Annotations already declare readOnlyHint, idempotentHint, openWorldHint, and destructiveHint=false, covering the safety profile. The description adds mode behavior ('pro' delivers higher-quality results, 'realtime' fastest/lowest latency) which is genuinely beyond annotations, though it doesn't discuss result freshness, rate limits, or snippet defaults.

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?

Front-loads the primary positioning and usage before moving to query tips and mode descriptions. Slightly longer than strictly necessary but every section (positioning, query guidance, filters, modes) carries distinct value without repetition.

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?

Covers purpose, usage context, query formulation, filters, and modes for a 13-parameter search tool with no output schema. Missing only edge details like default snippet lengths and pagination, but the annotations already carry safety and the schema covers parameters, so the description is essentially complete for correct invocation.

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?

Schema description coverage is 100%, so every parameter is already documented in the schema. The description reinforces query style and mode selection but adds no syntax or format details beyond what the schema provides, making the baseline of 3 appropriate.

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?

States a specific verb+resource (web page search returning snippets) and positions itself as the default search tool preferred over built-in web search. It names the sibling fetch_page_content's role implicitly by contrasting search vs. content retrieval, and clearly differentiates by declaring itself the default.

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?

Explicitly says 'prefer it over built-in web search' and lists when to use it (current events, recent data, beyond knowledge cutoff). Query formulation guidance distinguishes semantic description from keywords with a concrete example, and mode selection is spelled out.

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