request_run_cancellation

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

Annotations declare readOnlyHint=false, idempotentHint=false, and destructiveHint=false, but the description adds essentially nothing beyond 'Request cooperative cancellation'. It does clarify that interruption is cooperative and host-owned, which is a meaningful behavioral nuance, but it doesn't explain what the host does with the request, whether cancellation is guaranteed, or what the response indicates. For a tool with no readOnly safety and a cooperative semantics model, more disclosure would help.

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 a single short sentence, which is efficient with zero waste. However, it is under-specified rather than appropriately concise for a 3-parameter mutation tool with cooperative semantics.

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?

The tool has an output schema (helpful for return values), so some burden is lifted. However, the description is thin for a tool that mutates run state, requires an expected revision parameter (suggesting optimistic concurrency), and has three supported-parameter siblings like pause_host_run, resume_host_run, and acknowledge_run_cancellation nearby. The description doesn't explain what 'expected_revision' guards against, when a cancellation request would be rejected, or how it relates to the acknowledgment flow.

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 0%, so the description must compensate for absent parameter documentation. It does not mention any of the three parameters (run_id, expected_revision, reason) and doesn't explain the meaning of 'expected_revision' as an optimistic-concurrency guard or the purpose of 'reason' in a cooperative cancellation flow. A 0% coverage with no compensatory context is a significant gap.

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 uses a specific verb ('request') and clear resource ('run cancellation'), and notes the cooperative, host-owned nature of the interruption. While it doesn't explicitly distinguish itself from siblings like acknowledge_run_cancellation, the phrasing is generally clear about what the tool does.

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 provides no guidance on when to use this tool versus alternatives. Given the sibling set includes pause_host_run, resume_host_run, acknowledge_run_cancellation, and get_run_control, the agent has no help choosing between a cooperative cancellation request and other run-control operations. The description does not mention that acknowledge_run_cancellation is a distinct follow-up mechanism.

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