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 meaningful work: it names the answering layer (searxng, searxng-retry, browser:<engine>, cache), discloses the result fields, and warns that results are untrusted web content. Missing context is minor – no mention of rate limits, latency, or failure behavior.

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?

Three compact sentences, purpose front-loaded, then return shape, then the safety caveat. Every sentence adds information an agent can act on; no filler.

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 and the description still summarizes the return fields and the layer indicator, plus the untrusted-content warning – adequate for a simple 2-param search tool. The one real gap is the absent relationship to read_page and how results should be chained into it.

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. It explains max_results as an upper bound on returned results, but leaves the required query parameter's format entirely undocumented (plain text? operators? multi-term behavior?). Partial compensation only.

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 clear verb+resource ("Search the web") and enumerates the return shape, so the agent knows exactly what the tool does. It does not, however, distinguish itself from the sibling read_page, so an agent must infer the boundary between searching and fetching a 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?

No guidance on when to use this versus read_page, nor any preconditions (auth, query syntax). The only usage signal is implicit in the name and the return field list, which is not enough for a two-tool family.

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