Web search

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

Annotations already cover readOnlyHint=true and openWorldHint=true, lowering the bar. The description adds genuinely non-obvious behavioral context beyond those flags: the tool automatically fans out to multiple providers (html+wiki+duck) in keyless mode and switches to Brave when keyed. This discloses multi-backend behavior that an agent could not infer from the name or annotations.

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?

One sentence with high information density; the key differentiator (keyless-first, fan-out) is front-loaded. Every word earns its place. The minus is that compression crosses into jargon ("html+wiki+duck; brave when keyed") that costs a reader effort to decode.

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?

With an output schema present, return values need no description, and annotations cover the read-only/open-world profile, reducing the burden considerably. For a low-complexity tool (3 params, 1 required), the description covers the core routing behavior. Remaining gaps: what environment variable enables the keyed Brave path, and what the fan-out output looks like across providers. Adequate but with minor open questions.

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 carries the documentation burden. It partially compensates by explaining the backend auto behavior ("auto fans out... brave when keyed"), which illuminates the backend parameter's default. However, it says nothing about count semantics (8 results? pages?) and only implicitly covers query. The description does meaningful work for one of three parameters but leaves the others to inference.

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 conveys a specific action (search) over a specific scope (web, fanning out across html+wiki+duck, or brave when keyed). It differentiates from sibling wiki_search by explicitly including wiki among the fan-out targets rather than being the wiki-only tool, and from fetch_text/browser_fetch by being a search rather than a fetch. The telegraphic phrasing ("html+wiki+duck") is cryptic but not tautological.

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 implies usage context: use it when no API key is configured (keyless-first) and it will auto-route, switching to Brave when a key is present. However, it never explicitly states when NOT to use it or names alternatives (e.g., wiki_search for Wikipedia-only queries, fetch_text for fetching a known URL). The when-to-use is implied rather than stated.

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