Send Saved Draft

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

Annotations already declare the non-read-only, non-idempotent, non-destructive, open-world profile, and the description adds real context on top: required scopes mailbox.read and email.send, the conflict behavior on a stale revision, and the 30-day scheduling window. It does not discuss retry safety or what a successful send returns, but the output schema covers the latter.

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?

Four short sentences, front-loaded with the action before the prerequisites, and every sentence carries either a scope requirement or a conditional parameter rule. The dense, telegraphic phrasing ("Pass expected_revision") is efficient but leaves little room for orientation.

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 high-stakes mutation with six parameters, the description covers the safety-critical pieces: required auth scopes, revision pinning, conflict signaling, and scheduling conditions, while the output schema handles return values. Only multi-mailbox targeting (mailbox_id) and ETag handling are left entirely to the 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 coverage is 100%, so the baseline is 3, and the description earns more by explaining cross-parameter conditional requirements the schema cannot express — expected_schedule_version is needed only when scheduling or right after a cancellation. It does not mention mailbox_id or the If-Match parameter at all, so a small gap remains.

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 gives a specific verb and resource ("Send only the saved revision") and adds a scope qualifier — the exact approved revision, not the live draft — which implicitly separates it from a compose-and-send tool. It never names a sibling such as mailbox_send_message or the schedule-control tool, so the differentiation is inferable rather than stated.

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 concrete conditional guidance: pass expected_revision always, pass scheduled_for plus expected_schedule_version to schedule within 30 days, and include the current schedule version after cancelling a schedule. What's missing is an explicit "use X instead" pointer to the compose-new-message or schedule-modification tools.

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