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

With destructiveHint and idempotentHint annotations already declaring the destructive and idempotent nature, the description adds specific behavioral details: it aborts only starting/running runs, returns updated run details, and explains the graceful option with a 30-second timeout. This goes beyond the annotations without contradicting them, though it could mention edge cases like double-abort behavior.

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 well-structured: the main purpose is stated first, followed by behavioral details, then usage guidelines and examples. It is concise but includes an unnecessary repetition of 'Abort' in the USAGE line. The examples are helpful and the overall length is appropriate for the tool's complexity.

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 simplicity (2 params, one required), the description is complete: it explains the core action, the conditions under which it has no effect, the return of updated run details, the graceful option, and provides concrete examples. The presence of an output schema means the description need not detail return fields. No critical information is missing.

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?

Both parameters (runId and gracefully) are fully described in the schema (100% coverage), and the description repeats the graceful behavior without adding new information beyond the schema. Since the schema already explains the parameters thoroughly, the description provides no extra value here, warranting the baseline score of 3.

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 tool aborts an Actor run that is starting or running, and specifies that it has no effect on finished runs (SUCCEEDED, FAILED, ABORTING, ABORTED, TIMED-OUT). This precisely distinguishes it from sibling tools like get-actor-run (read-only) and call-actor (starts a run), leaving no ambiguity about the action and resource.

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 USAGE section explicitly says to use it when a run is 'taking too long or misconfigured,' and the no-effect statement implicitly warns against using it on already-finished runs. However, it does not explicitly name alternative tools (e.g., get-actor-run for checking status), so it falls short of the 'explicit alternatives' criterion for a 5.

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