Creates a Gmail draft email without sending it, letting you prepare recipients, subject, body, CC/BCC and account for later review or sending.
Create a draft (does not send). account is an email or alias.
| Name | Required | Description | Default |
|---|---|---|---|
| cc | No | ||
| to | Yes | ||
| bcc | No | ||
| body | Yes | ||
| account | No | ||
| subject | Yes |
Changes observed during successful MCP inspections.
v0.1.0Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations supplied, the description carries the full behavioral burden, and it does disclose the single most important trait: nothing is transmitted. It says nothing about where the draft lands, whether recipients are validated, what happens on a bad address, or what the call returns (e.g., a draft id), so the disclosure is useful but shallow.
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 its key constraint, with zero filler. Nothing could be removed without losing information.
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 mutation tool with no annotations, no output schema, and six undocumented parameters, the description should say more about result and side effects. The non-sending guarantee covers the highest-risk unknown, which keeps this from being inadequate, but the surrounding gaps remain.
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 0% across six parameters, so the description must compensate and it largely does not. Only `account` is explained ("an email or alias"); the format expected for the `to`/`cc`/`bcc` string arrays and whether `body` supports HTML are left entirely to inference.
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?
"Create a draft" is a specific verb+resource, and "(does not send)" immediately separates it from send_email and send_draft in the sibling list. It does not distinguish itself from create_reply_draft, which is the closest sibling, but the core action is 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 parenthetical "does not send" implies the selection condition against send_email/send_draft, but only by negation. There is no explicit "use this when..." guidance and no mention of when to prefer create_reply_draft or send_draft for an existing draft.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.