Web search

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

Annotations cover the safety profile (readOnlyHint, openWorldHint), and the description adds real behavioral context beyond them: results are ranked from the perspective of the `location` geography, snippets are truncated and not a substitute for the page, and URLs (including anti-bot-guarded pages) are readable via `scrape`. It stops short of stating rate limits, latency, or query-length constraints, but it is well above the annotation-only bar.

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?

Front-loads purpose, then usage conditions, then output/behavior caveats — a sensible information order. The middle paragraph is slightly long-form with some redundancy ('current events, news, prices' overlapping with 'latest'), but every sentence carries actionable content rather than 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, so return-value documentation is not required, yet the description still gives the useful shape (titles, short descriptions, URLs) and warns that snippets are truncated. Combined with explicit sibling routing and geographic caveats, an agent has everything needed to call this correctly and to know what to do next.

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%, so the baseline is 3, but the description adds genuine meaning the schema does not: ranking and pricing are resolved for the country in `location` rather than a global average, and unrecognised geo values are silently coerced (documented in the schema too). The query guidance in the schema ('keyword-shaped beats sentence-shaped') is not repeated, which is fine.

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?

Opens with a concrete verb+resource ('Search the live web') and immediately scopes the output ('ranked organic results'). It also draws the line against siblings by naming `scrape` as the follow-up tool for reading page content, so the agent can separate retrieval from reading without opening either schema.

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?

Explicitly enumerates when to use it (current events, prices, availability, versions, 'latest', past-cutoff facts, competitor research) and states the preference over a built-in web search or answering from memory. It also carries a clear negative case: 'Not for local files, git, or anything off the public web.'

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