send_draft

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

The description contradict the annotations: annotation declares idempotentHint=true, but the description explicitly warns 'must NOT be retried' when pending approval, implying non-idempotent behavior. This is a direct contradiction. Per scoring rules, this dimension scores 1. The description otherwise adds good behavioral detail (pending approval status, immediate send), but the contradiction overrides.

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 three sentences long, each serving a purpose: stating the action, providing usage context, and explaining the two possible outcomes. It is front-loaded with the core purpose and contains no fluff or redundancy.

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?

Given no output schema, the description adequately explains return values (202 with pending_approval or immediate message ID). It covers the main behavioral aspects. However, it does not mention error scenarios (e.g., draft not found, already sent) or address the idempotency conflict, leaving minor gaps. Overall, it is fairly complete.

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?

The input schema has 100% coverage with a clear description for the single 'id' parameter. The description adds no additional parameter semantics beyond what the schema provides. Baseline score of 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 clearly states the action ('Send a draft you prepared, by its id') and the tool's resource ('draft'). It distinguishes from sibling tools like send_email and reply_email by focusing on draft sending. The two modes (immediate vs pending approval) are succinctly described, making the purpose 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 description explicitly says 'Call this when a staged draft is ready to go out.' It also provides crucial guidance on the pending approval case: 'NOT a failure and must NOT be retried.' While it does not explicitly compare to send_email as an alternative, the draft context implies the distinction. The guidance is clear and actionable.

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