Create email draft

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

The no-send statement adds meaningful behavioral context beyond the bare annotations, and the annotations themselves (readOnly=false, destructive=false) are consistent with draft creation. However, the description does not disclose that drafts are persisted, that repeated calls create new draft instances, or how the draft lifecycle connects to send/discard operations, which would be useful for a mutation tool.

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, front-loaded with the action, and no filler. The sending caveat is placed at the end and earns its place because it prevents a likely misuse.

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 12-parameter tool with no output schema and only 2 required parameters, two sentences are insufficient. Important invocation details such as the need for sourceMessageId in reply/forward modes and what the tool returns (e.g., a draft ID) are absent, so an agent would have to infer or experiment to use it correctly in more complex scenarios.

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?

With 0% schema coverage, the description partially compensates by mapping mode values (new/reply/reply-all/forward) and naming To/CC/BCC, optional HTML, and allowlisted attachments. It omits semantics for sourceMessageId, quoteOriginal, includeOriginalAttachments, bodyText/bodyHtml relationship, and accountId, so it does not fully bridge the schema gap.

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 concrete action ('prepare') on a specific resource (email draft), enumerates supported modes (new/reply/reply-all/forward), and lists key components like To, CC, BCC, and HTML. It also explicitly separates the tool from sending, making it easy to distinguish from mail_draft_send at a glance.

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 opens with an explicit 'Use this to...' directive and includes a clear exclusion: 'It does not send email.' This prevents an agent from selecting it for sending, but it does not name alternatives like mail_draft_send or mail_draft_update, so the routing guidance is clear but incomplete.

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