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

With no annotations, the description carries the full burden and does well: it discloses partial-cancellation semantics (in-flight hops finish, queued hops no-op), required permission level, and the terminal-status error. It omits whether the action is idempotent or reversible, which would complete the mutation profile.

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 dense sentences, front-loaded with the operation and its effect before preconditions and errors. Every clause adds distinct information with no filler.

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 2-parameter mutation tool with no annotations and no output schema, the description covers semantics, authorization, and error behavior. Missing only secondary details like repeat-cancel behavior or what the caller gets back.

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%, so runId and the optional reason are already documented in the schema. The description adds no parameter-level detail (e.g. runId format or how reason is surfaced), so the baseline 3 applies.

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+resource (cancel a run) and immediately narrows scope with the exact cancellation semantics ('in-flight hops finish, queued hops no-op'). It does not explicitly contrast with the nearby sibling pause_run, but the verb and semantics still let an agent tell the two apart semantically.

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?

Gives concrete preconditions and a failure condition: editor access on the run's graph is required, and cancelling a run already in a terminal status errors. It stops short of explicitly routing the agent between cancel_run and pause_run/resume_run, which is the main missing piece.

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