create_draft

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

With no annotations, the description carries the full burden, and it does disclose the single most important behavioral trait for a mail tool: it never sends, only writes to the Drafts folder. It says nothing about permissions, whether an existing draft is overwritten, or what a successful call returns, so transparency is partial rather than rich.

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?

One sentence, front-loaded with the action and destination, ending on the safety-relevant constraint. No filler sentences and nothing redundant with the schema.

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 zero-parameter, no-annotation, no-output-schema tool, the description covers the essential risk disclaimer (never sends) but leaves a real gap: it never explains where the email content comes from given the empty input schema, nor what the call returns. Minimum viable rather than complete.

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?

Zero parameters, so per the baseline this scores 4; the empty schema leaves nothing to document. The description does not explain how the draft body is supplied, but with no parameters present there is no schema content to obscure.

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?

States a specific verb (Saves), resource (an email) and destination (Mail.app Drafts folder) in one clause, and the trailing negation ('it never sends') explicitly separates it from the many send-capable siblings (send_email, m365_send_email, agent_send). An agent can route between this and the send tools without opening either 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?

Gives clear context for use: drafting for human review and manual sending, which is exactly the case that distinguishes it from direct-send tools. It does not name an alternative tool explicitly or state prerequisites, so it falls just short of the top band.

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