create_draft

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

No annotations are provided, so the description carries the full behavioral burden. It clearly discloses the most important non-obvious behavior: the email is not sent immediately and is persisted in the Drafts folder. It omits return behavior or other side effects, but for a create-draft operation the critical behavior is covered.

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 front-loads the most important fact, that the email is not sent, followed by the destination. There is no filler or redundant restatement of the tool name.

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?

Together with the fully described schema, the description is nearly complete for a simple draft-creation tool. The main gaps are the lack of information about the operation's result, such as whether a draft ID is returned, and no explicit sibling alternative for sending.

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?

All seven parameters have individual descriptions in the schema, so schema coverage is 100%. The description itself adds no parameter-level meaning, which is acceptable because the schema already documents each field clearly. Baseline 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 states a concrete action: it saves an AI-generated draft to the Drafts folder rather than sending it. This explicitly distinguishes the tool from sibling sending tools like send_email and reply_email. The scope is unambiguous.

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 key usage boundary is clear: use this tool when you want to create a draft, not when you want to transmit an email. It does not name the alternative tool explicitly or list exclusions, but the contrast with sending is strong enough for an agent to route correctly.

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