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

Annotations already disclose destructiveHint=true and idempotentHint=true, so the safety profile is covered. The description adds genuinely new context: that it requires 'write' scope and that the cancelled message 'n'existe jamais pour le contact', clarifying the observable effect (no trace for the contact) beyond the annotation flags.

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 short sentences, zero filler, with the action and its pending-state constraint front-loaded before the scope and effect notes. 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 a one-parameter, no-output-schema mutation with rich annotations, the description covers action, precondition, scope, and user-visible effect. It stops short of stating error behavior for a non-pending or unknown schedule_id, which leaves a small gap.

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 100% and the single parameter already documents its UUID format and points to ficiel_list_scheduled as the source of the ID. The description adds nothing further about the parameter, so the baseline 3 applies.

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+resource ('Annule un message programmé') and constrains it with 'encore en attente', which cleanly separates it from ficiel_list_scheduled and ficiel_schedule_message. An agent immediately understands this cancels, not lists or creates.

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 phrase 'encore en attente' gives a clear applicability condition, and the required 'write' scope is stated, so the agent knows when it can and cannot be used. It doesn't explicitly name a fallback for already-sent or already-cancelled messages, but the pending-state qualifier covers the main routing decision.

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