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

Annotation Contradiction: the description states it 'deletes the draft row,' which conflicts with the destructiveHint=false annotation. The description otherwise adds useful behavioral detail (atomic conversion, delivery, return of new Message), but the contradiction with the annotation is serious and warrants a score of 1.

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?

Three tight sentences with no filler: action, mechanics, preconditions, return value. Every sentence adds necessary information and the core action is front-loaded.

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?

With one parameter, an output schema present, and annotations provided, the description covers all necessary operational details: what happens atomically, the deletion side effect, required draft fields, and the returned Message. The agent has enough to invoke correctly.

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 already documents the single 'id' parameter as 'Draft ID' with 100% coverage. The description does not add semantic detail about the parameter beyond what the schema provides, so baseline 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 a specific verb ('Send') and resource ('draft'), then explains the atomic transformation of the draft into a delivered Message and the deletion of the draft row. This distinguishes it from siblings like email_send and email_draft_* operations without needing to open schemas.

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 communicates the intended use by referencing an existing draft and states the preconditions (recipient, subject, body). It does not explicitly cite alternatives or when-not-to-use scenarios, but the draft-focused language makes the appropriate case clear.

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