web_search

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

Annotations already declare readOnlyHint and openWorldHint, so the description is free to add the interesting traits: no API key required, first-answering-engine fallback, and merge-by-agreement under engine=all. It also bounds the payload ('not the pages'), though it does not discuss rate limits or result-quality caveats.

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 dense sentences, each doing distinct work: mechanism, workflow/routing, return shape. No filler and the scope statement is front-loaded.

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 read-only search tool with no output schema, the description supplies the mechanism, the alternative tool, the downstream workflow, and the return fields (title, url, snippet). An agent has everything needed to select and call it 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 all three parameters are documented there, including the engine values and the limit default/max. The description's engine note ('the first engine with results answers, engine=all merges them') largely restates the schema rather than adding syntax or format detail, so the baseline of 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?

States a specific verb+resource ('Search the web') plus the mechanism ('reading public search engines' own result pages'), which distinguishes it from the fetch/crawl siblings. It also names the sibling it is not (web_site_search) for the single-site case.

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 ('find URLs for a topic'), the follow-up step ('then read them with web_fetch or web_fetch_many'), and an explicit when-not/alternative ('To search inside one site use web_site_search'). Routing is unambiguous.

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