Save Draft

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

With no annotations provided, the description carries the behavioral disclosure burden. It covers key traits: no message is sent, the draft appears in the user's mail client, and the user reviews and sends it. It could add more detail about side effects or permissions, but the central safety-relevant behavior is explicit.

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 sentences with no filler: the first front-loads the core purpose and no-send guarantee, the second provides the comparison to send_email and the usage condition. Every sentence earns its place.

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 6-parameter tool with an output schema, this description is complete enough: it states purpose, behavior, alternatives, and when to choose the draft path. Minor gaps such as explicit prerequisites or exclusions are not critical because the schema covers the parameters and an output schema exists.

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 100%, so the parameters are already documented in the input schema. The description adds no parameter-specific meaning beyond that, so the baseline 3 is appropriate.

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 states a specific action and resource: 'Prepare un brouillon dans le dossier Drafts, sans rien envoyer'. It clearly distinguishes itself from send_email by calling itself a safe alternative, so an agent can identify this tool's purpose without opening the schema.

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?

It explicitly names send_email as the alternative and gives a concrete selection rule: prefer this tool whenever the content deserves human review before departure. This is direct when-to-use guidance with an explicit alternative.

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