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

Annotations already declare idempotentHint=true, openWorldHint=true and non-read-only, so the safety profile is largely covered. The description adds real value by disclosing that a code is emitted with a ten-minute lifetime and by explaining how to retry safely. It omits what happens for an already-registered email, what is returned, and whether the code delivery is by email.

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 tight sentences with the primary action and its side effect front-loaded, followed by the retry semantics. Nothing is redundant. The only structural quibble is that the description is in French while the tool name, title and siblings are English, which adds friction for an English-speaking agent.

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 two-parameter flow-entry tool with annotations covering safety and idempotency, the description supplies the action, the observable side effect, the code lifetime and retry behavior. The lack of an output schema is the main residual gap, but the tool's contract is clear enough to invoke confidently.

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 0%, so the description must carry the load. It clarifies idempotency_key ('un texte ordinaire', reuse the same request after a lost response), which is genuinely useful since the schema only says string/1-128 chars. The email parameter gets no explanation at all, and neither parameter's format or validation behavior is described.

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 ('Démarre une inscription') plus a concrete side effect ('envoie un code valable dix minutes'), which distinguishes it from verify_account_signup and complete_account_signup. It stops short of naming those siblings, so an agent must infer that this is the entry point of the flow.

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?

Usage is implied by the word 'Démarre' and by the note about retrying after a lost response, but there is no explicit when-to-use/when-not guidance and no mention of the sibling tools. An agent can guess this is step one of signup, but nothing states preconditions (e.g. whether requirements must be fetched first via get_account_signup_requirements).

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