web_search

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

With no annotations supplied, the description carries the burden and does disclose key traits: read-only, idempotent, and that results are snippets rather than full page content (which matters for choosing web_reader). It omits rate limits, empty-result behavior, and whether snippets are truncated.

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 short sentences, front-loaded with the action and engine, then the use case, then the safety profile. No filler or repetition; 'read-only and idempotent' earns its place precisely because no annotations exist.

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?

For a two-parameter search tool with no output schema, the description covers purpose, trigger conditions, and the shape of returned results. The remaining gap is minor: it does not say what to do when results are insufficient (e.g., escalate to web_reader, which the sibling list suggests exists).

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 both 'query' and 'max_results' (with its 1-20 bound and default 5) are already fully documented structurally. The description adds no syntax, format, or query-construction guidance beyond what the schema provides, so baseline 3 applies.

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?

Specific verb+resource+engine: 'Search the live web using DuckDuckGo' and it enumerates what comes back (titles, URLs, text snippets). It does not name a sibling (e.g., web_reader for full-page content, get_news for curated feeds), so the boundary with the closest alternative is left to inference.

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?

'Use when you need current facts, external references, or breaking information not in your training data' gives a clear positive trigger tied to data staleness. No when-not guidance or pointer to web_reader/get_news for full content or curated headlines, so the exclusion side is missing.

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