create_draft

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

With no annotations provided, the description carries the full burden of behavioral disclosure. It does disclose the key behavior that the email is not sent, but it omits additional context such as authentication requirements, what is returned (e.g., draft ID), or whether the draft is saved to the user's drafts folder. For a simple creation tool, this is adequate but not rich.

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 a single sentence that is to the point, free of redundancy, and front-loads the essential information. Every word adds value: the action (create), the object (draft email), and the qualifier (without sending).

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 simplicity of the tool and the complete schema coverage, the description is mostly complete. It could mention that the draft is saved, but the lack of an output schema and the non-destructive nature of the action make this a minor gap. The presence of sibling tools also provides additional context for the agent.

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 100% description coverage for all 7 parameters, with each property having a clear explanation. The tool description itself adds no parameter-specific details beyond what the schema provides, so the baseline of 3 is appropriate.

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 uses a specific verb ('Create') with a clear resource ('a draft email in Gmail') and explicitly states 'without sending it,' which distinguishes it from the sibling tool send_email. It fully defines the tool's scope and action.

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 phrase 'without sending it' clearly implies that this tool is for preparing drafts rather than delivering emails, which provides a clear usage context. However, it does not explicitly name alternative tools (like send_email) or state when not to use this tool, so it lacks the strongest level of guidance.

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