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 so well: it discloses keyless operation, engine ordering, merge/de-duplication by URL, that 'google' is News RSS rather than a web index, that 'bing' is opt-in, and the exact failure shape ('error[KEYLESS_...]:' plus a Hint). Rate limits, latency across chained engines, and truncation behavior are not mentioned, which keeps it short of a 5.

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-loaded with purpose and result shape, then engine semantics, then edge cases. Dense but nearly every clause carries information; the sentence enumerating the inline result object is slightly verbose given an output schema exists.

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?

Despite an output schema being present, the definition covers the result fields, engine behavior, default ordering, result-count bounds, and the empty-array and error-code cases. An agent has everything needed to call it and interpret both success and failure responses.

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 0%, so the description must compensate, and it mostly does: it enumerates the engine values, explains that order matters and the list is merged/de-duplicated, and defines the default. The max_results 1-20 range merely repeats the schema's minimum/maximum, and 'query' syntax (phrasing, quoting, operators) is left unexplained.

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 web without an API key') and immediately characterizes the return value, so the tool is clearly distinguishable from web_fetch (which retrieves a known URL). It never names the sibling explicitly, so differentiation is implied rather than stated.

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 concrete selection guidance: engine order controls priority, omitting engines falls back to the server default (duckduckgo, then google, then wikipedia), and an empty array means 'retry with different terms or another engine'. What's missing is guidance on when to prefer web_fetch over searching, or when to include wikipedia/news engines for a given intent.

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