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

With no annotations, the description carries the burden of behavioral disclosure. It does disclose the key non-sending behavior and the sending-disabled edge case. However, it omits other relevant behavior such as whether the draft lands in the Drafts folder, whether it returns a draft ID, or whether any permissions beyond a connected mailbox are needed.

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?

Three short sentences with no filler. The core action is front-loaded, the user-facing role is clarified in the second sentence, and the environment condition is a valuable third sentence. Every sentence earns its place.

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 description is adequate for a straightforward draft-creation action and conveys the essential no-send distinction. However, with no output schema and no annotations, the agent is left without information about the return value, confirmation behavior, or any content-format expectations, making it incomplete for a 7-parameter tool.

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 only 29% (2 of 7 parameters described: mailbox and replyToMessageId). The tool description adds no parameter-level guidance for to, cc, bcc, subject, or body, and does not clarify body format (plain text vs HTML) or reply-threading details beyond the schema's brief replyToMessageId note.

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 opens with a specific verb and resource: 'Write a draft into the mailbox without sending it.' This clearly distinguishes it from send_gmail_message and create_outlook_draft, and the follow-up 'The person opens and sends it themselves' reinforces the no-send intent.

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 explicitly contrasts drafting with sending and even provides a concrete use-case condition: 'Works even when a workspace has switched sending off.' It does not explicitly name send_gmail_message as the alternative for immediate sending, but the distinction is strongly implied and easy for an agent to act on.

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