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

Annotations only convey non-readonly, non-idempotent, non-destructive. The description adds an unusually complete operational contract: daily BODACC/AMF/PSAN/Seveso/ICPE checking, Ed25519-signed webhook vs email digest, bearer-token polling, 7-day expiry reminder, pay-per-target pricing per duration, no pro-rata refund, and the critical spendControls client-cap failure mode that would otherwise cause silent rejection before the API is ever called. This vastly exceeds what annotations provide.

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?

Purpose is front-loaded and every major section earns its place: selection criterion, monitoring scope, delivery, pricing, refund policy, and the spendControls prerequisite. Some redundancy exists where the pricing breakdown (including -10%/-17.8% discount percentages) is repeated in both description and schema, which could be trimmed without loss.

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 6-parameter, payment-gated creation tool with an output schema, the description covers everything needed for correct invocation: when to use it, what is monitored daily, how events are delivered, the exact cost model, both payment paths (x402 vs api_key), and the client-side cap fix. Return values are handled by the output schema, so no essential context is missing.

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 description coverage is 100% and the schema descriptions are already rich: cibles format (1-100 SIRENs/dirigeant entries), duree enums with unit prices, api_key credit fallback and precedence over x_payment, and the quote-vs-payment behavior of x_payment. The description reinforces the payment flow but adds no parameter meaning the schema lacks, so the high-coverage baseline of 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?

Description states a specific verb+resource ('create a 30, 90 or 365-day watchlist over French companies and/or directors'), scopes the target to France, and names the monitored entities (companies, directors). The 'OUTLASTS the check' framing separates it from the one-shot get_* siblings, and the create/renew/stop/get lifecycle siblings are distinguished by the unique creation action.

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?

Provides an explicit selection rule: 'use when the relationship OUTLASTS the check (supplier, borrower, portfolio company)', which clearly marks the boundary against one-time checks and implies the when-not case. However, it never names a specific alternative sibling (e.g., check_french_regulator_alerts or get_french_company_legal_alerts), leaving the alternative identification to inference.

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