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

Annotations indicate the tool is not read-only and not destructive. The description adds the precondition that the action must be 'preparee non confirmee', but it does not disclose side effects (e.g., whether the action is deleted or marked as cancelled), nor does it mention any authorization or state change details beyond the 'leads.write' scope.

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?

The description is a single, succinct sentence that front-loads the core purpose. It contains no filler and is appropriately concise for a simple tool.

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 low-complexity tool with one parameter and no output schema, the description covers the essential purpose and precondition. It does not mention return values or error handling, but given the simplicity of the operation, this is an acceptable level of completeness.

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 schema has a single integer parameter 'action_id' with no description (0% schema coverage). The description implies that the tool cancels an action, so 'action_id' likely refers to the identifier of the action to cancel, but it does not explicitly state this or clarify how to obtain the ID. The description partially compensates but leaves some ambiguity.

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 the verb 'Annule' (cancel) and the specific resource 'action preparee non confirmee' (prepared unconfirmed action). It distinguishes this tool from the sibling 'confirmer_action' by focusing on cancellation of unconfirmed actions, making its purpose unambiguous.

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 description specifies the condition 'non confirmee', implying it should be used only for prepared actions that haven't been confirmed yet. It provides a clear usage context but does not explicitly contrast with alternatives like 'confirmer_action' or mention exclusions beyond that condition.

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