web_search

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

Annotations indicate readOnlyHint=true, openWorldHint=true, idempotentHint=true. The description adds valuable behavioral context beyond these annotations: 'Results stay fresh for 30 minutes; use time_range to get more recent results,' 'Snippets are not the full source — use scrape_page before asserting a claim,' and 'Zero results do not confirm a fact is false.' These details help the agent understand caching, evidence limitations, and the open-world nature, aligning with the openWorldHint.

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 concise (four sentences) and front-loaded with the primary purpose. Each sentence adds distinct value: the core capability, parameter-based narrowing, alternative tools, and critical caveats about freshness and evidence. No redundant or filler content.

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?

For a tool with 14 parameters and an output schema, the description covers the essential context: what it does, when to use alternatives, important behavioral traits (freshness, snippet limitations), and the open-world caveat. The schema handles parameter details, and the description clearly communicates the tool's role within the sibling set, making it complete for an AI agent.

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 the schema fully documents each parameter. The description adds minimal extra parameter meaning by referencing site and lens usage ('Narrow results to one domain with the site parameter, or apply a search lens') and mentions time_range for recency, but this is lightweight. Since the schema already provides thorough parameter descriptions, the baseline of 3 is appropriate; the description does not significantly exceed the schema's existing guidance.

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 clearly states what the tool does: 'Search the web and get a list of relevant pages with titles and snippets — without reading the full page content.' This is a specific verb+resource (search the web) and explicitly distinguishes from siblings by naming search_and_scrape, news_search, and academic_search as alternatives for different needs.

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 provides explicit usage guidance: use search_and_scrape for full page text, news_search for current events, academic_search for research papers. It also explains how to narrow results with the site parameter or apply a lens for trusted sites, and mentions time_range for recency. This clearly communicates when to use this tool versus alternatives.

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