messagerie_enregistrer_brouillon

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

Annotations already declare readOnlyHint=false, destructiveHint=false, idempotentHint=false and openWorldHint=false, so the safety profile is covered. The description adds one meaningful behavioral fact — the draft is stored, not sent — but says nothing about permissions, whether re-saving with the same brouillon_id overwrites, or what identifier is returned.

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?

A single sentence, front-loaded with the primary action, with the workflow detail parenthesized rather than padding a second paragraph. Every clause carries information.

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 an 8-parameter mutation with no output schema and annotations covering the safety profile, the description covers purpose and the create/attach/send lifecycle adequately. It leaves the return value unspecified, though the parenthetical implies the created draft ID is what `brouillon_id` feeds into.

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 75%, so most parameters (`a`, `cc`, `cci`, `corps`, `objet`, `en_reponse_a`, `transfert_de`) are already documented in the schema. The description only adds meaning for `brouillon_id` by tying it to the subsequent messagerie_envoyer call; it adds nothing about the other seven parameters.

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 pair and resource ('Crée ou met à jour un brouillon') and immediately differentiates it from the send path ('sans l'envoyer'), naming the related siblings messagerie_joindre_fichier and messagerie_envoyer. An agent can tell this is the draft-staging tool and not the sender without opening 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 workflow guidance: use it to hold a draft, attach files via `messagerie_joindre_fichier`, then send via `messagerie_envoyer` with `brouillon_id`. It names the sequencing context but offers no when-not guidance (e.g. when to just call messagerie_envoyer directly, or how it relates to messagerie_supprimer/restaurer).

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