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

Beyond the read-only, idempotent annotations, the description discloses that results are keyword-based rather than legal, that the tool does not approve accounts, and that pasted text is neither stored nor echoed back. The PII exclusion adds an actionable handling constraint that annotations cannot express.

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?

It is front-loaded with the trigger, then inputs, then outputs, then caveats and data-handling rules. Every sentence adds distinct information, and the ordering follows the decision an agent actually makes.

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 only needs to characterize results, which it does by naming the found/missing gap categories and the suggested-fix payload. Combined with the caveats and data-handling note, an agent has everything needed to call this correctly for a five-parameter tool.

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 goes further by framing subscriptions, delivery model, and statement descriptor as optional inputs tied to specific checks (renewal terms, delivery timing, descriptor). This tells the agent why each optional field matters, not just that it exists.

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 opens with a concrete verb and resource: it checks pasted refund, cancellation, shipping, or terms text for merchant-account review readiness. This is clearly distinguishable from sibling tools like build_application_checklist or check_dispute_ratio, which build artifacts or audit different signals.

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 trigger is explicit: use when a merchant pastes policy text and asks whether it is ready for review. It also states boundaries — a keyword check, not a legal review, and not an approval — plus a 'do not include' exclusion for customer names, order details, and financial data. It does not name a sibling alternative, which keeps it shy of a 5.

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