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

Annotations already declare destructiveHint=true and idempotentHint=true; the description reinforces and extends them by explaining that the run's current state is returned either way and that already-settled runs come back unchanged rather than as an error. That 'never an error' semantics is genuinely useful context an agent cannot infer from the hints alone.

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?

Tight, front-loaded single sentence that leads with the action and appends the API mapping and edge-case behavior. The stray 'looot:' prefix is dead weight, but everything after it earns its place.

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 mutation with no output schema, the description covers operation, API equivalence, and the non-error return behavior — enough to call it correctly. It stops short of stating permission/auth requirements, but nothing essential is missing.

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?

One required parameter (runId) with 0% schema description coverage, so the description carries the burden and adds nothing about the id's format or expected values. runId is largely self-evident from its name, so this is adequate but not enriching.

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 and resource ('cancel a queued or running run') and pins it to the underlying API operation (POST /v1/runs/{id}/cancel). The verb 'cancel' is inherently distinct from every sibling (runs_get, runs_list, runs_evidence, run), so an agent can route to it unambiguously.

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?

Usage is implied by the verb: use it to cancel a queued or running run. It does not say when not to use it or point at a sibling (e.g., runs_get) to check state first, and the API-equivalence note is mapping info rather than decision guidance.

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