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

The description goes well beyond the minimal readOnlyHint=false annotation. It discloses that nothing is sent, the draft lands in Gmail's Drafts folder, the body must be plain text, current read-only connections cannot create drafts, and the tool will indicate failure if the grant is absent. No contradiction with annotations.

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 somewhat long but every sentence earns its place: core behavior, non-sending guarantee, content guidelines, usage routing, and a permission caveat. It is front-loaded with the essential action and only slightly dense in the middle.

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 create-draft tool with sparse annotations and no output schema, the description covers the essential operating context: what the draft is, where it goes, what to write, when to use the tool, and the grant limitation. An agent has enough information to invoke it correctly and to anticipate failure.

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 100%, so the parameters are already fully documented. The description reinforces the body format ('plain-text body (no HTML or markdown)') and the 'in the user's voice' guidance, but it does not add substantial meaning beyond what the schema already provides.

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 specific verb and resource: 'Create a DRAFT email in the user's connected Gmail mailbox' and clarifies that nothing is sent, distinguishing it from send_email. However, it does not differentiate from the closely named sibling draft_email_in_gmail, which weakens the distinction among siblings.

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?

Explicitly states when to use the tool ('Use this whenever the user wants an email written to someone else') and contrasts it with send_email ('remains only for mailing the user their own address'). It also flags the legacy modify grant restriction, which is important context for when the tool will fail.

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