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

The description adds a meaningful behavioral caveat beyond the annotations: cancellation is best-effort and a run already finishing may still complete. The annotations already cover destructive and idempotent behavior, so this is appropriately supplemental rather than duplicative.

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 short sentences deliver the core action, the scope, and the key caveat with zero redundant phrasing. The most important information is front-loaded.

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 simple cancellation tool with full schema coverage, an output schema, and annotations covering destructiveness and idempotency, the description provides the remaining essential context: what states are cancellable and the best-effort nature of cancellation.

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?

All three parameters already have descriptions in the schema (100% coverage), including the environment pinning detail and runId provenance. The tool description adds no additional parameter-level meaning, so the baseline score of 3 is appropriate.

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 names a specific verb ('Cancel'), a specific resource ('split run'), and narrows the scope to 'queued or in-flight' runs. It clearly distinguishes this from sibling cancel_* tools by focusing on the split-run resource type.

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 communicates clear context: use this to cancel a split run that is either queued or currently in flight. It does not explicitly name alternatives like delete_split_run or cancel_classify_run, but the scope is clear enough for an agent to infer correct usage.

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