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

Annotations already declare destructiveHint=true, idempotentHint=true and readOnlyHint=false, so the safety profile is covered. The description adds genuinely new behavior beyond the annotations: the call is a no-op for SUCCEEDED/FAILED/ABORTING/ABORTED/TIMED-OUT runs, and the response returns the updated run details. It does not mention permission requirements or failure modes.

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-loaded with the core action and its status preconditions before the USAGE block, and no sentence is wasted. The USAGE EXAMPLES lines are thin (one is a bare restatement of the required runId) but the graceful variant does demonstrate a real parameter usage.

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 an output schema present, return values need not be detailed, and the description correctly just notes that updated run details come back. Purpose, preconditions, and usage are all covered; only permission/auth context is missing for a destructive, openWorld=false operation.

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 description coverage is 100% and both parameters (runId, gracefully with its 30-second timeout) are fully documented in the schema, so the baseline is 3. The description adds little parameter meaning beyond the example 'Gracefully abort run y2h7sK3Wc', which only loosely illustrates the gracefully flag.

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 ('Abort an Actor run') and narrows scope with the precondition 'currently starting or running', which makes the operation unambiguous. It never names a sibling such as get-actor-run to contrast against, but the destructive abort semantics are self-evidently distinct from the read-only tools in the sibling list.

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?

'Use when you need to stop a run that is taking too long or misconfigured' gives a clear triggering condition, and the status no-op list functions as an implicit when-not-to-use rule for terminal runs. No alternative tools or host-level prerequisites (auth, workspace scoping) are offered, so it stops short of a full routing guide.

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