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 behavioral burden. It does disclose that results are live and returns structured source fields, which implies a read-only, non-mutating operation, but it says nothing about rate limits, cost, result freshness/latency, or failure modes when the web is unreachable.

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?

Four short sentences, front-loaded with purpose then use cases then syntax then follow-up. Every sentence is useful, though the operator sentence partially restates the schema's own query description.

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 an output schema present, the description needn't detail return values, and it still gives a useful one-line summary of them. It covers purpose, when to use, query syntax, and sibling handoff; only behavioral caveats (rate limits, freshness) are missing, which is a modest gap for a read-only search tool.

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 already documents all five parameters including count, localization, need_content, and ori_question. The description's operator list (site:, -site:, -, "exact phrase", lang:, after:, before:) largely duplicates the query parameter's own schema description rather than adding new semantics. Baseline 3 is 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?

Opens with a specific verb+resource ('Search the live web') and immediately states the return shape (structured sources with title, url, snippet, summary, publish date, authority). It is clearly distinguishable from its only sibling web_fetch, which is scoped to reading a single page.

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 names the trigger conditions: recent events, facts that cannot be confirmed from memory, anything past the training cutoff. It also routes to the alternative ('Follow up with web_fetch to read a page in full'), so an agent knows the division of labor between the two tools.

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