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

Annotations already declare destructiveHint=true, readOnlyHint=false and openWorldHint=true, so the safety profile is covered. The description reinforces this with 'Action financière réelle' and adds the concrete precondition that the order must be paid, but leaves out whether partial refunds exist, idempotency, or failure/irreversibility behavior.

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?

Two short sentences, zero filler, with the action front-loaded and the financial-risk warning second. Nothing to trim.

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 destructive, open-world financial mutation with no output schema and 0% parameter documentation, the description is too thin: it says nothing about full vs partial refund, currency/amount handling, what the response confirms, or what happens when the refund fails.

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 0% — the single `id` property is an undocumented positive integer. The phrase 'd'une commande' partially compensates by implying the value is an order identifier, but it never states this explicitly or gives the expected identifier source/format.

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?

Names a specific verb/resource pair (request a Stripe refund on an order) and even constrains scope to 'une commande payée'. It is clearly distinguishable from siblings like cancel_subscription or cancel_booking because it names Stripe and the refund action, though it does not explicitly contrast them.

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 'commande payée' qualifier implies the precondition for use, and 'Action financière réelle' signals this is not a dry run, but there is no explicit when-not guidance or named alternative (e.g., cancel_subscription for recurring charges) to route the agent.

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