adaptorch_cancel_run

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

Annotations already declare destructiveHint=true, idempotentHint=false and openWorldHint=true, so the safety profile is covered. The description adds one genuinely useful nuance beyond that with the word 'Request' — cancellation is requested, not guaranteed or immediate — but it stops short of saying what happens to in-progress work, whether retries are safe, or what happens if the run already finished.

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 tight sentence with the operation front-loaded and zero filler. It is efficient; the only critique is that the budget was spent so narrowly that no routing or behavioral context fits.

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 destructive mutator with annotations carrying the safety profile and no output schema, the description is roughly sufficient to invoke it correctly. It omits the post-call story — async nature, how to confirm cancellation, behavior on already-terminal runs — which matters for a destructive non-idempotent 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 0%, so the schema gives no meaning for run_id, but the description at least ties the parameter to the operation ('by run_id'). With a single self-describing identifier this is adequate, though the expected format or source of a run_id — presumably from adaptorch_run or adaptorch_list_runs — is never stated.

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 specific verb ('Request cancellation') and resource ('an in-flight run') plus the identifier, so an agent can distinguish it from adaptorch_run and adaptorch_get_run without inspecting schemas. It never names a sibling or explicitly contrasts itself, so it stays short of a 5.

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?

'in-flight run' implicitly scopes when the tool applies, hinting it is not for completed or queued runs. But there is no explicit when-to-use, no guidance on what to do instead for a finished run, and no mention of adaptorch_get_run for polling status after the cancel request.

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