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

Annotations declare readOnlyHint=false and openWorldHint=true, and the description explains exactly why this is not a pure read: a search can spawn a collection, each new place costs one credit, and cost is capped by `limit`. It additionally discloses the API key requirement and the 60-second `wait` ceiling, well beyond structured fields.

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 the purpose and the free-cached-results benefit, then the cost/collection mechanics, then follow-up and auth. The middle sentence is dense with a colon and multiple clauses, but each sentence carries distinct information 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?

For a complex, credit-metered, partially-asynchronous tool with no output schema, the description covers the mechanics an agent must understand: caching, collection creation, per-place cost, the limit cap, and how to retrieve late arrivals. It does not describe the shape of returned place objects, which is the main remaining gap.

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 baseline is 3, but the description layers on real meaning: `limit` doubles as the maximum credit cost of a search, and `wait` is framed as waiting for newly collected places rather than a generic timeout. That cost binding is not derivable from the schema alone.

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 and resource ('Find places') and grounds it with a concrete example ('bakeries in Curitiba'), including both the 'what' (keywords) and 'where' (geo) axes. It is unmistakably distinct from the sibling set, which is dominated by collections, exports and webhooks.

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 clear operational context: results already saved return instantly and free, and 'search again later, or read the collection, to get the new ones' tells the agent how to follow up. It stops short of naming sibling tools or stating explicit when-not-to-use conditions, so it is strong but not fully directive.

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