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

Annotations already cover read-only, idempotent, non-destructive behavior, so the bar is lower. The description still adds value beyond them: answer text is third-party and marked untrusted (a safety trait the agent must respect), only the latest measurement is returned (no historical data), and pagination is fixed at 10 per page.

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?

Content is front-loaded with what is returned, then the trust caveat, then the page size — a sensible order. It is dense and slightly run-on in the field enumeration but every clause carries information; no filler sentences.

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, the description needn't document return structure, yet it still summarizes the payload, flags the untrusted-text property, and states the page size. The remaining gap is behavior when no measurement exists yet, which the agent would have to discover.

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 every parameter (site, cursor, engine) is fully documented in the schema itself, including the enum values and the multi-site fallback behavior. The description's only parameter-adjacent detail, '10 per page', largely restates what the cursor description already says ('next 10 items'), so baseline 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?

The description names a specific verb and resource ('the answers recorded in the latest measurement') and enumerates the returned fields (question, engine, named/cited, businesses and sources, excerpt), so an agent knows exactly what data comes back. It distinguishes itself implicitly from siblings like get_ai_sources or get_ai_visibility by focusing on individual answer records, but never names an alternative explicitly.

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?

'Latest measurement' implies this should be read after run_ai_measurement, and 'answers' implies per-answer retrieval rather than aggregate visibility. However, no sentence states when to choose this tool over get_ai_visibility, get_ai_sources, or get_ai_traffic, so the routing is left to inference.

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