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

Annotations only declare destructiveHint=true, so the description carries real weight and delivers it: it says work in progress is stopped, that cancellation cascades to all unfinished workflows/jobs/attempts, and that cancelled jobs remain retryable. It omits permission requirements and behavior on an already-finished run, but the destructive scope is well disclosed.

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?

Three tightly packed sentences, front-loaded with the 'WRITE — stops work in progress' signal so the destructive nature is the first thing read. Every sentence carries distinct information: mutation semantics, scope, and recovery path.

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 single-parameter, no-output-schema mutation, the description covers the essentials an agent needs: it is a write, its cascade scope, and the follow-up retry tool. Only edge-case behavior (cancelling an already-completed run, idempotency) is left unaddressed.

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%, with run_id already documented as 'CI run id, from depot_ci_list_runs.' The description adds no format, sourcing or validation detail beyond the schema, so the baseline of 3 applies; 'Depot: CIService/CancelRun' is an internal endpoint reference, not parameter guidance.

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?

States a specific verb ('Cancel') plus resource ('a queued or running Depot CI run') and enumerates the blast radius: all unfinished workflows, jobs and attempts. This clearly distinguishes it from sibling read tools like depot_ci_get_run_status and from the retry siblings, which restore rather than stop work.

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?

Establishes context by naming the qualifying states ('queued or running') and points to depot_ci_retry_failed_jobs as the recovery path after a cancellation. It does not state when NOT to cancel (e.g. already-completed runs) or how it relates to per-job cancellation via depot_ci_retry_job, so it stops short of explicit alternatives.

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