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

The description discloses critical behavioral traits beyond the annotations: it 'SPENDS MONEY', requires specific billing state, is bounded by credits and caps, and enforces a deduplication rule (repeat on the same day replays the original result regardless of key). This is exactly the kind of context an agent needs to avoid unexpected costs and understand idempotency semantics.

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?

The description is information-dense, with the prominent 'SPENDS MONEY' warning front-loaded. Each clause earns its place, covering purpose, prerequisites, limits, and dedup behavior. However, it is structured as a single long run-on sentence with semicolons, which reduces readability; a bulleted list would have been clearer.

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 paid, rate-limited operation, the description covers operational essentials: cost, auth, idempotency, and quotas. However, it does not describe the return value or whether the scan runs synchronously or asynchronously; since no output schema is provided, a brief note on expected response would improve completeness.

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 schema already includes descriptions for both parameters (scan enum and idempotency_key), and the description adds little new meaning beyond restating that the key is client-minted. Since schema coverage is 100%, the description does not need to compensate, but it also does not enrich the parameter semantics further.

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 clearly states the tool's action: 'run an on-demand AI visibility scan' with the specific scan type 'ai_visibility' and its purpose (GEO measurement of answer engine representation). This distinguishes it from sibling tools like get_visibility or get_competitors, which likely retrieve existing data rather than trigger a new scan.

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 gives strong when-to-use context: it triggers a paid, on-demand scan and outlines prerequisites (write scope, paid plan/trial, idempotency key). It also warns about credit limits and daily caps. However, it does not explicitly name alternative tools for reading existing results, such as get_visibility, so the guidance is clear but not fully comparative.

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