web_search

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

With no annotations provided, the description carries full burden. It discloses the backend (DuckDuckGo HTML), the cost structure (no API key, no per-query cost), and the return structure (list of title, url, snippet). However, it omits potential behavioral traits like rate limits, error handling, or behavior when no results are found. This is adequate but not rich.

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?

The description is a single, well-structured sentence that immediately states the tool's core value (free web search), backend, and return format, then ends with a useful pointer to fetch_url. Every word earns its place, making it highly efficient and easy to parse.

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 simple search tool, the description covers the essential aspects: what it does, what it returns, and how to get full content. It lacks explicit guidance on when to prefer this over documentation search tools, but given the tool's simplicity and the pointer to fetch_url, it is mostly complete. A mention of result limit behavior would make it fully complete.

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?

The schema describes 'query' but not 'limit', and the description adds no clarification for 'limit' behavior (e.g., number of results, default). It only indirectly implies that results are limited but without specifics. Since schema coverage is only 50%, the description should compensate for the undocumented 'limit' but fails to do so.

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?

The description clearly states it is a 'web search' tool that 'Returns a list of {title, url, snippet}', identifying the specific verb (search), resource (web), and output format. It also differentiates from the sibling 'fetch_url' by explicitly directing users to pass URLs there for full content, firmly establishing its distinct role.

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?

The description provides clear context for usage: it's a free web search without API key or cost, implying it's for general web queries. It explicitly mentions 'Pass any URL to fetch_url for full content', offering a clear alternative for fetching full page content. However, it does not explicitly mention when to use 'lib_docs' or 'search_docs' instead, so exclusions are not fully stated.

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