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

The annotations already declare readOnlyHint=false and destructiveHint=true, so the description does not need to restate basic safety. It adds valuable behavioral context beyond annotations: nothing is sent, watermarked drafts are refused until unlocked, the legacy-grant limitation is surfaced at call time, and the return value is a link to the draft. It does not explain what the destructive hint specifically covers, but it does not contradict the annotations either.

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 front-loaded with the main action and safety statement, then covers the unlock requirement, grant limitation, and return value in compact sentences. Every sentence adds relevant information for correct invocation.

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 four-parameter write-like tool with no output schema, the description is complete enough: it explains the generated-email source, the no-send behavior, the unlocking prerequisite, the legacy-grant constraint, and the return value. Remaining parameter details are fully covered by the rich schema.

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 schema already documents all four parameters. The description adds minimal extra meaning, mainly reiterating that artifact_id comes from generate_email and that recipients were named by the user; it does not add syntax or edge-case guidance beyond the schema.

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: putting a generated email artifact into the user's Gmail drafts. It distinguishes this from sending by saying 'Nothing is sent' and ties the artifact to generate_email, so an agent can differentiate it from siblings like send_email and create_gmail_draft.

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 clear context for when to use the tool: with an artifact_id from generate_email, addressed to named recipients. It also states two important preconditions — the email must be unlocked and the mailbox must be connected under a legacy modify grant — though it does not explicitly name an alternative for drafting non-generated emails.

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