create_draft

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

Annotations already declare destructiveHint=false and idempotentHint=false, so the safety profile is partly given. The description adds meaningful behavior beyond that: the draft is opened in Mail for user review and, critically, 'Never sends' – confirming no message reaches recipients. It does not say what happens if a draft is re-created or whether an existing draft is overwritten.

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 short sentences, front-loaded with the action and closed with the key guarantee. No redundant restatement of the name or title.

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?

Output schema exists, so return values need no explanation, and the description covers modes, the review step, and the no-send guarantee. What remains thin is permission/prerequisite context and draft-collision behavior, but the core picture is sufficient for correct 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 coverage is 71% and the schema already documents id, to, body, subject and the mode values. The description mirrors the mode list ('reply, reply-all or forward') but adds no syntax, format, or edge-case meaning for cc/bcc or the interaction between id and to beyond what the schema states.

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 and resource (write a new message / reply / reply-all / forward) plus the outcome (opens it in Mail as a draft). The 'Never sends' clause sharpens the distinction from any send-like operation, though no sibling tool is named explicitly.

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?

Usage is implied by 'for the user to review' – this is the composing path that leaves the message in the user's hands. There is no explicit when-not guidance or reference to alternatives such as open_in_mail or read_mail, so the agent must infer the boundary.

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