create_draft

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

With no annotations, the description must carry behavioral disclosure. It correctly discloses the most important behavior: it does not send. However, it does not mention that this creates a persisted draft in the user's mailbox, potential permissions needed, or any side effects beyond draft creation.

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?

A single sentence that front-loads the verb and resource, immediately states the key constraint, and contains zero filler. This is a model of concise, efficient tool description.

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 tool with no annotations and no output schema, the description is too sparse. It does not explain what happens after draft creation, how the draft can be accessed for review, or important parameter constraints. An agent is left to infer everything about the draft's lifecycle beyond creation.

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 0%, so the description needed to compensate, but it adds no parameter-level guidance. Property names like to_recipients, subject, and body are self-explanatory, but the description does not clarify formats, requiredness, body_type options, or recipient separators. The tool description is entirely silent on parameters.

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 'create' and the resource 'mail draft', and adds 'does not send' to distinguish it from send-related siblings like send_mail and send_draft. The purpose is unambiguous even without a title.

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 'for user review (does not send)' conveys when to use this tool versus sending tools. It does not explicitly name alternatives, but the negative constraint effectively routes an agent away from send operations. Slight deduction for not naming siblings like send_draft or send_mail.

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