Create a Gmail draft

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

The description adds value beyond annotations by explaining the draft stays in Drafts folder, is safe to call freely, and requires user review. Annotations lack details, so the description carries the burden well.

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 lean sentences front-load the core purpose and safety. No wasted words; every sentence serves a clear role.

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?

While the description covers purpose and safety, it omits parameter guidance and return value info. For a tool with no output schema, more detail on parameter semantics would improve completeness.

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%, meaning half the parameters lack descriptions. The tool description does not add any parameter-specific details (e.g., no explanation of 'threadId' or 'cc/bcc' format), leaving the agent with gaps.

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 it creates a draft in the Drafts folder and explicitly distinguishes from sending by stating 'This does NOT send anything'. The verb 'create' and resource 'draft' are specific, and it contrasts with sibling tool 'send_email'.

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 context for when to use ('when not fully sure the user wants to send yet') and implies safety. However, it does not directly compare to 'send_email' or state when not to use it.

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