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

Annotations already establish this is a non-read, non-destructive, closed-world creation, so the bar is lower. The description adds two pieces of real behavioral context beyond them: the readiness prerequisite tied to product state, and the crucial clarification 'Ne crée aucun paiement' — the tool builds the page, not a charge. It does not say whether the call is idempotent (requestId) or what happens to an existing page for the same product.

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 short sentences, front-loaded with the action, then the conditional constraint, then the most important negative clarification. Zero filler and no repetition of the title.

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 creation tool with a nested free-form config object and no output schema, the definition covers the essentials and the schema itself points at describe_payment_pages for config shape. The remaining gap is what a successful call returns (the created page id/URL) and the meaning of requestId, both of which an agent would benefit from knowing before invoking.

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 only 20% (just the config object), so the description must carry weight. It meaningfully constrains the status parameter (active requires an active product; prefer draft for staging), which is genuine semantics not in the enum, but name, productId, and requestId get no explanation — notably requestId's idempotency role is never clarified.

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 verb and resource: 'Créer un formulaire de paiement pour un produit du projet' — an agent immediately knows this creates a payment page bound to a product. It is distinguishable from update_payment_page and describe_payment_pages, though it never names those siblings explicitly, which is why it stops short of a 5.

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?

'Actif exige un produit actif ; préférer draft pour préparer' gives concrete selection guidance on the status enum and a stated prerequisite for the active case. What is missing is routing guidance toward describe_payment_pages for the config payload and toward update_payment_page for post-creation changes, so the when-to-use picture is clear but not complete.

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