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

With no annotations, the description must carry the behavioral burden. It usefully discloses the key side effects—nothing is sent and the thread remains open—but omits what happens to the draft's state afterward, permissions needed, and whether rejection is reversible.

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?

Two short sentences, front-loaded with the action and immediate consequence. Every phrase adds useful meaning, with no filler.

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?

For a simple two-parameter action with full schema coverage and no output schema, the description covers purpose and the main behavioral outcome. It could mention the draft's resulting state, but that is a minor gap given the schema already documents parameters.

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 both parameters are documented there, including that the reason is kept with the draft. The description adds no parameter-level meaning beyond identifying the draft as the object being rejected, so the 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?

States a specific verb ('turns a draft down'), the resource (draft), and the critical consequence ('sends nothing'). It implicitly separates the action from approve_draft and send_email by making rejection non-sending and leaving the thread open.

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 clear context for using it: reject the draft without sending and keep the thread open for another answer. It does not explicitly name approve_draft as the alternative or state when not to use it, so it stops short of full routing guidance.

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