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

Goes well beyond the annotations by specifying the concrete consequence ('Sending deletes the draft and returns the message'), approval-mode behavior (HTTP 202 pending owner approval), conflict handling (409 draft_sending), paused-inbox behavior (403 inbox_paused), and that allow/block/suppression lists are checked. This is exactly the kind of operational detail the destructiveHint annotation cannot convey.

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?

Front-loads the core trigger ('Use this when a draft should be sent now') before the detail, and every clause carries operational weight. The dense run-on of error codes is information-rich but slightly over-packed; a 4 rather than a 5.

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 no output schema, the description carries the return-value burden and does so ('returns the message'), while also covering permissions, approval flow, idempotency, list checks, and failure codes. An agent has everything needed to call it correctly and interpret outcomes.

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% and each parameter already carries a description, so the schema does the heavy lifting. The description largely restates the input list (required vs optional) without adding syntax or format meaning beyond what the schema provides. Baseline 3 applies.

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 opens with a specific verb+resource: 'Use this when a draft should be sent now.' It is unambiguous that this operates on an existing draft. It does not, however, explicitly distinguish itself from the sibling cooper_send_message, leaving the draft-vs-message distinction to be inferred.

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?

Provides a clear when-to-use condition ('when a draft should be sent now') plus explicit prerequisites: requires auth and message_send or draft_send scope, and 'draft_write alone cannot send.' No explicit alternative or when-not is named, but the precondition guidance is strong.

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