draft

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

No annotations are provided, so the description carries the full burden. It discloses that the tool opens a conversation with pre-filled text without sending, allows accents, and requires an explicit user command plus a separate act call with verification to send. Core behavioral profile is clear.

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?

Front-loads purpose, then gives parameter formats and sending flow. The structure is logical but sentences are long and somewhat run-on, with conditional instructions mixed in. It earns its length by covering required semantics, though could be tightened.

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?

No annotations or output schema exist, so the description must supply context. It defines the tool's scope, parameters, and the follow-up act path for sending, which is complete enough for an agent to draft and know how to send. Some edge cases (e.g., missing conversation, contact ambiguity) are omitted.

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 compensate. It thoroughly defines 'to' formats (contact name, phone number, bracket conversation number) and 'app' enum (sms/RCS or whatsapp), and notes accents are permitted for 'text'. It does not elaborate on 'text' beyond that, but all parameters receive meaningful guidance.

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 (Préparer) and resource (une réponse) with scope (sans l'envoyer) and behavior (ouvre la conversation avec le texte déjà écrit). It distinguishes itself from the act sibling by describing the sending path separately. An agent can identify it among siblings like act or messages.

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?

Explicitly instructs to use act only if the user explicitly says « envoie » for this draft, naming the alternative (act) and the condition. This provides clear when-to-use and when-not-to-send guidance, leaving little to inference.

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