create_draft

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

With no annotations provided, the description bears full responsibility for behavioral disclosure. It mentions that recipients and subject are derived when replying, and that replyAll works with replyToMessageId. But it does not state that the tool performs a write operation, requires authentication, or what happens on success. Important behaviors like error conditions or side effects are omitted.

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 extremely concise: two sentences that communicate the core action and the most important usage variant (reply drafts). Every sentence is informative and earns its place, with no filler.

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?

Given the tool's complexity (10 parameters, no output schema, no annotations), the description is too brief. It does not explain how to handle combinations of parameters (e.g., both to and replyToMessageId), the creation lifecycle, or the output. The presence of sibling tools like update_draft and delete_draft indicates a draft lifecycle, but the description does not orient the agent to this context.

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?

The input schema has 90% description coverage, so the schema already explains most parameters. The description only adds value for replyToMessageId and replyAll by explaining their interplay. For other parameters like cc, bcc, attachments, the description offers no additional meaning beyond what the schema provides, meeting the baseline expectation.

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 'Create a draft' clearly states the verb and resource. It further distinguishes from siblings like update_draft and send_email by specifying that for reply drafts one should pass replyToMessageId, implying that without it, a new draft is created. This makes the purpose specific and 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 provides explicit guidance for reply drafts: 'For a reply draft, pass replyToMessageId (recipients/subject are derived; replyAll for reply-all).' This helps the agent choose the right parameters. However, it does not cover when to use this tool versus other draft operations (e.g., update_draft) or when not to use it (e.g., for forwarding).

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