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

Annotations already mark the operation destructive, non-read-only, and idempotent. The description adds meaningful behavioral context beyond that: it is best-effort and may not stop a run that is already finishing, which is useful for setting agent expectations.

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 sentences with no filler. The main action and scope are front-loaded, and the best-effort caveat is appended compactly without repeating schema or annotation information.

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 three-required-parameter cancel operation with an output schema and clear annotations, the description is largely complete. The only omission is an explicit statement of what happens if the run is already completed or not found, but the best-effort caveat and output schema mitigate this.

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 each parameter, runId, environment, and workspaceId, already has a rich description including granted-target constraints. The tool description itself adds no parameter-specific semantics, 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?

The description clearly identifies the verb (cancel) and resource (classify run), and adds the key scope 'queued or in-flight' and '(classify group)'. It is unambiguous from the sibling cancel_* tools, though it does not explicitly name a sibling alternative as a differentiator.

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 gives a clear condition for use: cancel a queued or in-flight classify run, and warns that a run already finishing may still complete. It does not explicitly state when to prefer delete_classify_run or get_classify_run, but 'cancel' versus 'delete' and the queued/in-flight scope imply the boundary.

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