create_draft

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

With no annotations, the description carries the burden, and it discloses the main non-obvious behaviors: the email is not sent, the reply carries recipient/subject/thread metadata from the original, and the call returns the draft id. It doesn't discuss failure modes or rate limits, but the key side effects are covered.

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 tight sentences, front-loaded with the primary purpose and return value, then the conditional reply behavior. 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?

For a 10-parameter tool with no output schema and no annotations, the description plus sparse schema leaves important gaps: body/cc/bcc/html are not explained, and the requiredness contradiction between description and schema could cause an agent to construct an invalid draft. The reply flow is well explained but the rest is incomplete.

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 only 40%, so the description must compensate. It adds useful conditional meaning for reply_to_message_id and the to/subject override, but it conflicts with the schema's required list by declaring 'to' and 'subject' required when schema only requires account and body, and it leaves body/html/cc/bcc semantics undocumented.

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 object—'Create a draft email'—and adds the crucial '(not sent)' qualifier plus the return value ('Returns the draft id'). This clearly distinguishes the action from sending or list-only siblings.

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?

It gives explicit conditional guidance: provide reply_to_message_id to draft a reply inside the original thread, and states when 'to' and 'subject' are required versus optional. It doesn't name alternative tools, but the draft-vs-send distinction supplies clear context.

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