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

The annotations show no hints (readOnly=false, destructive=false), but the description proactively discloses the guarded approval flow and how rejection feeds into the drafter's prompt. It also clarifies that this is equivalent to user actions in the dashboard, setting expectations about permissions. This goes beyond schema and annotations, providing useful behavioral context. No contradiction with annotations.

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 concise, starting with the core behavior, then the feedback loop, then the guarded flow. Each sentence adds value and there is no fluff. It is well-structured for quick scanning.

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 the tool's moderate complexity (3 params, no output schema), the description covers the main aspects: what it does, the guarded flow, and safety equivalence. It doesn't describe return values, but since there's no output schema, that's a minor gap. Overall, it provides enough for an agent to call it 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 documents all parameters with descriptions (coverage 100%), so the baseline is 3. The description adds minimal extra parameter info; it mentions 'reason' is fed back but doesn't add format or syntax details beyond the schema. Thus, the description doesn't significantly enhance parameter understanding, and the schema already handles it well.

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: rejecting a queued autopilot action with a reason. It also conveys the impact of the reason on future drafts, which is meaningful context. While it doesn't explicitly name sibling approve_autopilot_action, the contrast with that sibling is implicit in the description's focus on rejection, so it effectively differentiates the purpose.

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 explains the guarded flow with approval_token, telling the user to call again with the token after confirmation. It also notes that dashboard guardrails apply, implying a safety context. However, it doesn't explicitly say when to use this over approve_autopilot_action or other alternatives, but the overall behavior is clear enough for an agent to know when to invoke it.

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