gmail_create_draft

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

The description discloses a key behavioral trait: the tool only creates a draft and does not send it. It also mentions that gmail_send_draft is gated on allowedRecipients, which is useful context. However, there are no annotations provided, so the description carries the full burden. It doesn't mention other behaviors like whether the draft is saved to the user's drafts folder or if there are any side effects, but the core non-sending behavior is clearly disclosed.

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 two sentences with no wasted words. The primary action is stated first, and the critical distinction from the sibling tool is front-loaded. 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?

For a draft-creation tool with no output schema and no annotations, the description is fairly complete. It clearly states the tool's purpose and the key behavioral boundary (no sending). The schema covers the parameters. The only minor gap is that it doesn't describe what the response looks like (e.g., draft ID), but since there is no output schema, that could be a small omission. Overall, it's sufficient for an agent to invoke the tool correctly.

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 50%, so the schema already documents several parameters (to, body, account, replyToMessageId, and the attachment variants). The description itself doesn't add parameter-level detail beyond what the schema provides. The description's main contribution is the non-sending behavior, which is not parameter-specific. Baseline 3 is appropriate because the schema covers half the parameters, and the description doesn't need to repeat that.

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 clearly states the tool's function: 'Create a Gmail draft.' It also explicitly distinguishes it from gmail_send_draft, which is a sibling tool, by noting that this tool does not send. This is a specific verb+resource combination that an agent can easily differentiate from the other Gmail tools.

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 says 'This tool does not send: use gmail_send_draft, which is gated on the account's allowedRecipients list.' This provides clear when-to-use guidance and names the alternative tool, making it easy for an agent to decide between creating a draft and sending one.

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