Create a Gmail draft

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

The description discloses a critical behavioral trait beyond the annotations: the tool only saves a draft and does not send it. It also adds workflow context about how drafts are eventually sent (human or gmail_send_draft). This is valuable context not present in the annotations, though it does not cover permissions or return format.

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, front-loaded with the action, and every sentence earns its place. It is concise without sacrificing key distinction from sending tools.

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?

The description conveys the essential purpose and the key distinction from sending tools, but lacks context about return values, how to reference the draft later, or details on parameter formats. Given the low schema coverage and no output schema, the description is only moderately complete, sufficient for a simple draft-creation tool but with notable gaps.

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 17% (only reply_to_message_id has a description), and the description provides no additional meaning for parameters like 'to', 'subject', 'body', 'cc', or 'account'. It does not compensate for the low schema coverage, leaving the agent without guidance on how to fill these fields beyond their names.

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 and resource: 'Save a draft in the account', which clearly states the core action. It also distinguishes from sibling tools by explicitly noting that drafts are not sent by this tool and mentioning gmail_send_draft as the sending alternative, differentiating it effectively.

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 provides clear usage context by stating that drafts are never sent by this tool and that sending is done by a human or gmail_send_draft after confirmation. This implicitly tells the agent when to use this tool (to create a draft without sending) and names a key alternative, though it does not enumerate all alternatives like gmail_send for immediate sending.

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