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

Annotations already declare destructiveHint=true, idempotentHint=true and readOnlyHint=false, so the safety profile is covered. The description adds the state effect ('end without an outcome') and an equivalence note, but does not say what is destroyed or whether the run becomes unrecoverable/purged.

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 sentences, front-loaded with the core action before the qualifying context. The second sentence ('Same effect as finishing on the run's addresses') is somewhat cryptic but short and adds a behavioral note.

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 destructive mutation with annotations covering idempotency and destructiveness and no output schema, the description covers the action and a usage context. It leaves the required run_id and the reason parameter unexplained, which is a real gap.

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 coverage is 0% and the description mentions neither of the two parameters. The required run_id and the optional 200-char reason are left entirely to the schema, so the description fails to compensate for the coverage 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?

States a specific verb and resource ('End a run without an outcome') and implies differentiation from rig.run.finish by contrasting 'without an outcome' against a normal finish. It never names the sibling, but an agent can infer the cancel-vs-finish distinction.

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?

'for a test that was abandoned' gives a clear when-to-use context. There is no explicit when-not clause or named alternative (e.g. rig.run.finish), but the abandoned-test framing is a usable selection signal.

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