gmail_create_draft

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

Annotations already indicate non-readonly and non-destructive behavior, but the description adds the critical behavioral detail that the draft is NOT sent and appears in Drafts for a person to review. This is important context that complements the annotations and clarifies the actual side effect.

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 exceptionally concise, with each sentence contributing meaningful information. It front-loads the core action, emphasizes the non-sending behavior, and concludes with the safety rationale, all in three short sentences.

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, the description covers the essential behavior and safety profile. It lacks details about output or follow-up workflow with gmail_send_draft, but the required parameters are in the schema and the tool's purpose is sufficiently clear for correct invocation.

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 only 20%, and the description adds no parameter guidance beyond what the schema provides. Only 'to' is documented as 'Comma separated'; cc, bcc, subject, and body receive no additional semantic explanation, leaving the agent to infer expected formats.

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 ('Write') and resource ('a draft'), and immediately distinguishes itself from sending by stating 'It is NOT sent.' This clearly separates it from sibling tools like gmail_send_draft and leaves no ambiguity about what the tool accomplishes.

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 clearly conveys the intended context: creating a draft for human review rather than sending it directly. It frames the tool as 'the safe way to have an agent write email,' which implies when it should be preferred, though it does not explicitly name the alternative gmail_send_draft.

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