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

The description goes beyond annotations by specifying the concrete consequence: the run is finalized as failed with message 'Cancelled by the caller'. It also lists the applicable run states. Annotations already declare destructiveHint=true and readOnlyHint=false, so the mutation nature is known; the description adds the specific outcome, which is valuable context. No contradiction with annotations.

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?

The description is two sentences with no filler. The action is front-loaded ('Stop a run...'), followed by the specific states and the outcome. Every word contributes to understanding the tool's behavior.

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 straightforward mutation tool with a single parameter and an output schema present, the description covers the essential aspects: the action, applicable states, and the resulting failure status. It does not address edge cases like invalid run_id or already-completed runs, but those are implicitly handled by the state condition and are not necessary for basic usage.

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?

The input schema fully documents the single parameter run_id, including its type and format (trun_...), so schema description coverage is 100%. The description does not add any extra semantic information about the parameter beyond what the schema already provides. Given high coverage, a baseline of 3 is appropriate; no further compensation is needed.

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 uses a specific verb 'stop' with the resource 'run' and clearly enumerates the eligible states (pending, running, waiting for input). It also explains the outcome (finalized as failed with a cancellation message), which unambiguously distinguishes this mutation tool from read-only siblings like get_run and list_runs, and from wait_for_run which is the opposite action.

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?

It explicitly states the conditions under which the tool applies: a run that is pending, running, or waiting for input. This gives clear context for when to invoke cancel_run. However, it does not mention alternatives or exclusions (e.g., what to do if the run has already finished), but the stated states are sufficient for most scenarios.

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