web_search

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

With no annotations, the description carries the full burden and does well: it discloses the result shape ('Returns links, not page content'), the source (Wikipedia), the cap (up to 5 links), the cost ($0.0035 USDC per call) and p99 latency (600ms). It stops short of payment/auth mechanics, rate limits or failure behavior for a paid per-call endpoint.

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 what the tool returns before routing guidance, and every sentence carries distinct information (result shape, subject fit, two alternatives, cost, latency). The only near-waste is restating that query is required, which is negligible.

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?

There is no output schema, but the description fully characterizes the return (abstract + up to 5 links from Wikipedia) plus cost and latency, which is everything an agent needs to invoke and price the call correctly.

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 coverage is 100% and the schema itself supplies query examples, so the description's 'Params: query (required)' adds nothing beyond the schema. Baseline 3 is appropriate when the schema does the heavy lifting on a single-parameter tool.

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 search) and pins down the exact output: a plain-language abstract plus up to 5 Wikipedia links, with named subject domains (people, places, concepts, history, science). It explicitly distinguishes itself from search_read (content retrieval) and news_search (breaking news), so an agent can select it without opening any schema.

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?

Gives explicit when-to-use ('Best for people, places, concepts, history and science'), an explicit when-not ('Not for breaking news'), and names the two alternative tools with the condition that selects each (search-read for page content, news-search for current events). Nothing is left to inference.

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