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

Annotations already declare destructiveHint=true and idempotentHint=true, but the description adds context annotations cannot carry: in-progress work is lost and the run's status settles to 'stopped' a few seconds later (asynchronous completion). It also names the required role and scope, which is essential for a destructive mutation.

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 tight sentences, front-loaded with the action and its consequence, then the requirements, then the disambiguation. Zero 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 destructive one-parameter mutation with no output schema, the description covers the loss of work, the async status transition, the auth requirements, and the sibling disambiguation. Nothing needed to call it correctly 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?

Schema coverage is 100% and the single sandboxId parameter is already documented in the schema as 'the run's sandbox id, from list_agent_runs'. The description adds no syntax or format detail beyond that, 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 and resource ('Stop the agent in one run before it finishes') and immediately scopes it against the sibling stop_mission. An agent can distinguish this from stop_mission and pause/resume without opening either schema.

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?

Explicitly says this stops one agent run and not the mission, and names the alternative route (POST /v1/missions/{issueId}/stop) for the mission-wide case. It also states the prerequisite role (org admin) and scope (sandboxes:stop).

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