messagerie_envoyer

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

Annotations already flag this as a non-read-only, non-idempotent, open-world write, so the safety profile is covered. The description adds genuine behavioral value beyond that: the recipient-ID sourcing requirement and the mandatory user-validation-before-send step for a real outbound message. It stops short of describing failure handling or whether attachments are sent inline.

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 tight sentences, front-loaded with the action and immediately followed by the two operational constraints. No filler or redundancy.

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 send tool with no output schema, it covers modes, recipient sourcing, and a pre-send validation requirement, which is enough for correct invocation. Minor gaps remain around attachment handling (a sibling, messagerie_joindre_fichier, exists) and send-vs-draft behavior.

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 75%, so the schema already documents `a`, `cci`, `brouillon_id`, `en_reponse_a` and `transfert_de`. The description reinforces the recipient-ID semantics and ties objet/corps to user validation, but adds little beyond the schema on the reply/forward/draft 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 and resource ('Envoie un message') and even enumerates the three modes it supports (new, reply, forward), so the agent knows the tool covers all three. It does not, however, contrast itself with the sibling messagerie_enregistrer_brouillon, even though brouillon_id is a parameter here.

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 clear context: recipients are identifiers obtained via `annuaire_rechercher` or read from an existing message, which tells the agent where to source them. Adds a workflow constraint (have subject, body and recipients validated by the user before sending) but no explicit when-not guidance or alternative-tool routing.

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