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

Annotations already declare destructiveHint=true and idempotentHint=true, covering the safety profile. The description adds useful context by restricting cancellation to queued or running runs, but does not disclose side effects such as whether results become unavailable or whether cancellation is reversible. This adds a similar level of value as the calibration example where annotations carried the safety burden.

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?

A single sentence with no filler words. The core action, resource, and state constraint are all conveyed efficiently, and nothing needs to be trimmed.

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 one-parameter tool with annotations covering destructiveness and idempotence, this description is nearly complete. It covers what the tool does and the applicable run states. It could mention handling of completed or nonexistent runs, but that is a minor gap for such a simple 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%, so the single run_id parameter is already documented as an 'AgentFarm run identifier.' The description adds no additional parameter semantics beyond implying the run must be queued or running, so the baseline score 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?

The description states a clear verb (Cancels) and resource (queued or running run), which distinguishes it from sibling tools like create_run, get_run_status, and get_run_result. The phrasing 'authenticated queued or running' adds scope but is slightly ambiguous about whether it refers to runs belonging to the authenticated user or runs with authentication state.

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 implies when to use the tool — when a queued or running run needs to be stopped — but does not explicitly mention when not to use it or reference alternative tools. The state restriction (queued or running) provides useful context, but exclusions are left to inference.

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