schedule_draft

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

The description provides rich behavioral details beyond the destructiveHint annotation: content is snapshotted, the draft is not auto-marked sent/deleted, send timing depends on process lifetime, and cancellation is possible. No contradictions 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 fairly long, but every sentence carries essential caveats for safe usage. It is front-loaded with the core purpose and uses 'IMPORTANT' to highlight critical constraints, making it efficient despite its length.

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 thoroughly covers the tool's runtime behavior, limitations, cancellation, cleanup, and relationship to other tools. A minor gap is the lack of any mention of the return value or success/error indicators, which is notable since no output schema is provided.

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 baseline is 3. The description adds meaning to draftId by explaining content is snapshotted at schedule time, and to sendAt by explaining best-effort timing and startup fallback. However, it doesn't add detail for the 'confirmed' parameter 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 clearly states the tool's function: 'Queue a saved draft to send at a future time instead of immediately.' It uses a specific verb+resource, distinguishes itself from send_draft (immediate send) and cancel_send (cancellation), and 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?

Explicitly explains when to use (to delay delivery) and critical when-not-to-use: 'this only fires while this MCP server process stays running' and 'not a reliable scheduler.' It also names alternatives ('Cancelable via cancel_send') and advises follow-up actions like checking list_drafts or get_email_stats after firing.

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