web_search

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

No annotations are provided, so the description carries the full burden. It usefully discloses two behaviors an agent could not otherwise predict: results come back ranked with ids (S1..), and each call consumes a limited budget. It says nothing about rate limits, quota exhaustion, or error/auth behavior when the budget runs out.

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 short sentences, front-loaded with the purpose and then the return shape. Every clause earns its place, with no restatement of the title or name.

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?

An output schema exists, so the description is not obliged to detail return values, yet it still surfaces the ranked-id convention and the budget dimension. Missing only prerequisites linking session_id to research_start and any fallback behavior, which keeps it just under a 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?

Schema description coverage is 80% and the schema itself documents site, query, freshness, and max_results, so the description need not re-explain them. The description adds no parameter-level meaning beyond the schema, which is the expected baseline here.

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 ("Search the web") plus its scope ("within a research session"), which is enough to separate it from research_start and research_approve. It does not explicitly distinguish itself from the closest sibling, web_fetch, so it stops short of a 5.

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?

"Within a research session" implies the tool requires a session established by research_start, but there is no explicit when-to-use or when-to-prefer-web_fetch guidance and no exclusions. Usage is inferable rather than stated.

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