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

Annotations already declare this as a non-read-only but non-destructive mutation, so the safety bar is partly covered. The description adds genuinely useful behavior: the run must be in flight, the state change is reversible via resume, and pausing does not bypass the approval gate — a real semantic restriction not expressible in annotations. Idempotency (calling pause twice) and error behavior are not addressed.

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 tight sentences with zero filler; the core action comes first and the constraints follow. Every clause carries distinct information (state change, reversibility, approval gate, invalid source states).

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 single-parameter, fully annotated mutation tool this is close to complete: preconditions, reversibility, and the approval-gate guarantee are all covered. There is no output schema, so a brief note on what the call returns or confirms would close the remaining gap.

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?

Only one parameter exists and schema description coverage is 100%, with the schema already stating it is the numeric run ID sourced from list_autopilot_runs. The description adds no additional meaning about the identifier, so the baseline of 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 and resource ('Suspends an autopilot run') plus the state precondition ('still in flight'), which implicitly separates it from resume and kill operations. It does not explicitly name the sibling tools, so the differentiation is inferable rather than stated outright.

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?

Gives a clear negative condition — 'A completed or failed run cannot be paused' — which tells the agent when the call will not work. It stops short of naming an alternative (e.g., kill_autopilot_run) for runs the agent wants terminated rather than suspended, leaving the agent to infer that routing.

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