Create an email draft

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

Annotations indicate readOnlyHint=false (non-read-only) and destructiveHint=false (non-destructive), so the description should clarify side effects. It adds that the draft is stored server-side in the Drafts folder, which is useful, but it does not mention whether a new draft is always created, whether it overwrites, or what the response contains. Given the annotations, the description provides some added context but not comprehensive behavioral 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 sentence that is concise, front-loaded with the core purpose, and contains no redundant or irrelevant information. Every clause adds value, from 'never-sent' to 'selected identity'.

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?

The tool has an output schema, so return values are covered. The description covers the core action and key distinction (draft vs. sent) and mentions 'selected identity,' which relates to the from_identity parameter. Minor gaps exist: it does not explain behavior when from_identity is omitted or clarify whether a fresh draft object is always created, but these are not critical for invocation.

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 all six parameters are already described in the schema. The tool description adds no additional parameter-level detail beyond the overall purpose. Baseline 3 is appropriate since the schema does the heavy lifting and the description does not add meaning beyond that.

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 verb ('Create'), a resource ('draft'), and a precise location ('server-side Drafts folder'). It also clarifies the draft is 'never-sent,' which distinguishes it from send_email and reply_email. This makes the tool's 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 implies usage for drafting rather than sending ('never-sent draft'), but it does not explicitly contrast with alternatives like send_email or reply_email, nor state when to choose this tool over them. There is no explicit 'when not to use' guidance, leaving the routing partially to inference.

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