draft_send

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

With no annotations provided, the description carries the full burden of behavioral disclosure, and it performs well: it details the hard policy gate (allowlist check on all recipients), the block behavior (draft left intact), and the timing guarantee (detection before any destructive operation, so a blocked send is a pure no-op). The only gap is that the success path (what happens to the draft after a successful send) is left implied rather than stated.

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 core purpose is front-loaded in the first sentence, followed by the safety-critical policy gate explanation. Each section earns its place given the eligibility risk. There is modest redundancy at the tail — 'detected BEFORE any destructive operation... pure no-op' partly restates 'left INTACT' — but overall the structure is efficient and well-organized.

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 tool is safety-critical, and the description covers the essential operational context: the allowlist gate, blocked-state behavior, and remediation routes. Given the output schema likely documents return values and the schema covers the single parameter fully, nothing an agent needs to invoke the tool safely is missing. Success-path side effects are the only notable omission.

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%, and the sole parameter draft_id is already well documented in the schema as 'Id of the saved draft to send.' The description adds no additional parameter semantics beyond the schema, so the baseline 3 applies — acceptable given the schema does the heavy lifting.

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 opening sentence 'Send an existing draft' is a specific verb+resource that clearly states the action. It is explicitly differentiated from siblings with 'THIS IS THE ONLY SEND TOOL', which separates it from draft_create, draft_update, and draft_delete in the same family. The naming claim is assertive and gives an agent unambiguous selection criteria.

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 states when to use this tool (to send a saved draft) and, importantly, what to do when the send is blocked — edit via draft_update or handle manually in Mail.app. It provides clear context for the post-block workflow. However, it does not explicitly contrast against email_send_html, a sibling that might be a competing send path, leaving that differentiation to inference.

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