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

Annotations already declare readOnly/idempotent/non-destructive, and the description goes well beyond them: 24-hour link validity, the two values returned, the subscription requirement with its free exception, and the failure behavior ('refuse, sans rien facturer ni démarrer de paiement'). That is exactly the billing/auth context an agent cannot infer from structured fields.

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 action and validity window are front-loaded, followed by usage routing and then the precondition, which is a sensible order with no filler. It is dense but slightly overloaded in the final clause about subscription and non-billing, which could be trimmed without losing the tool's core selection signal.

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?

Complete for a single-parameter read tool: annotations cover the safety profile, an output schema exists, and the description still adds the expiry, the subscription gate, and the refusal semantics. An agent has everything needed to call it and to predict failure modes.

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 the single document_id parameter is already documented in the schema, including its origin ('renvoyé par generate_document ou list_documents'). The description adds only the account-scoping notion ('du compte'), so the 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?

States a specific verb and resource ('Renvoie un nouveau lien de téléchargement du PDF') plus the exact output ('et le lien du document dans l'application') and the scope ('pour un document du compte'). It explicitly distinguishes itself from generate_document, so an agent can separate it from siblings without reading any schema.

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?

Gives concrete trigger conditions ('quand un lien précédent a expiré', 'pour un document retrouvé avec list_documents') and names the correct alternative for the adjacent intent ('pour générer, utilisez generate_document'). It also states a negative condition (no creation/modification) and a precondition (active subscription, with the état des lieux exception).

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