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

Beyond the supplied annotations, "envoi réel" clarifies that this is an actual send rather than a draft or preview, while the description also discloses template, consent, and connection constraints. It does not explain whether sending is immediate or queued, nor does it cover retries, idempotency, or failure 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 front-load the consequential action and then state the connection prerequisite, with no filler. The parenthetical about Meta-approved templates is compact and useful.

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 externally consequential send with no output schema, the definition leaves the essential `id` workflow and result behavior unspecified. The safety prerequisites are helpful, but the agent still cannot tell how to obtain the identifier, what exact send operation it represents, or whether the call merely queues delivery.

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?

The sole required parameter, `id`, has no schema description, and the description never explains what it identifies. It could refer to a contact, campaign, template, conversation, or prepared message, and the plural reference to "contacts" makes that mapping especially ambiguous.

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?

The description clearly states that the tool initiates a real WhatsApp send using a Meta-approved template to opted-in contacts. It adds meaningful scope beyond the title, but does not explicitly distinguish the operation from send_conversation_message, queue_outreach_messages, or the other channel-specific send tools.

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 approved-template, recipient-opt-in, and WhatsApp-connection requirements provide concrete preconditions for use. However, there is no guidance on when to use this tool instead of queued outreach or another messaging sibling.

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