Répondre à un email

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

With no annotations provided, the description carries the full burden. It discloses the irreversible nature and the real sending effect, which is critical behavioral context. It also warns about the confirmation requirement. However, it does not mention any side effects like what happens to the original email or whether it updates status, but for a simple reply action, this is adequate. The irreversibility warning is a strong disclosure.

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, purpose-built sentence that front-loads the critical warning about irreversibility and the mandatory confirmation step. There is no fluff or redundancy; every word earns its place. The structure is efficient and immediately conveys the core message.

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?

Given the tool's simplicity (3 parameters, 2 required), no output schema, and no annotations, the description effectively covers the essential contextual elements: it states the action, stresses irreversibility, and mandates user confirmation. The parameter details are already in the schema, so nothing essential is missing. It could have mentioned the replyAll option, but the schema covers it, so this is sufficient.

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%, so the schema already documents all three parameters (body, itemId, replyAll) with descriptions. The tool description does not add any additional meaning beyond what the schema provides. Since the schema is complete, a baseline of 3 is appropriate; the description does not need to repeat parameter details.

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 action: sending a real reply to an existing email. It uses a specific verb ('envoie') and identifies the resource ('un email existant'). It also distinguishes itself from siblings like forward_email or send_email by emphasizing 'réellement' (really) and the irreversibility, setting it apart as the actual sending action.

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 explicitly mandates that the agent must always ask explicit confirmation from the user before invoking this tool, specifying both content and the reply/Reply All choice. This provides a strong usage guideline, though it does not explicitly compare with alternatives. The warning is clear and actionable, making it a high-quality usage rule.

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