check_endpoints

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

Adds meaningful context beyond the annotations: it discloses that Trends has no public API, that endpoints can change without notice, that roughly 12 requests are sent, and that results are never served from cache. The annotation set (readOnly, idempotent, openWorld, non-destructive) already covers the safety profile, and the description enriches it with cost and caveat detail.

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 sentences, each earning its place: what it does, why it exists, and when to run it. The purpose is front-loaded and the framing caveat follows naturally.

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 detail is not required. For a zero-parameter diagnostic, the description supplies the why, the when, and the operational cost (requests, cache behavior), leaving nothing an agent needs to invoke 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?

The tool takes no parameters, so the baseline is 4; the description correctly implies it is argument-free by describing a fixed probe of all endpoints. No additional parameter semantics are needed or missing.

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 action (probe each Google Trends endpoint with a small request) and the output (which ones answer). An agent can immediately distinguish this diagnostic tool from the data-retrieval siblings like interest_over_time or trending_now.

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 names the trigger condition ('Run this when a tool fails unexpectedly') and the diagnostic decisions it disambiguates: rate-limiting, endpoint change, or network failure. This routes the agent away from guessing or blindly retrying failed sibling calls.

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