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

With no annotations, the description carries the full burden and does real work: it discloses the destruction scope (the task plus all processes it spawned), the blast-radius boundary (sandbox survives), the return value ("final state (killed)"), and the auth requirement. It omits irreversibility and error behavior for already-terminated tasks, which keeps it from a 5.

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 short sentences, front-loaded with the action and scope boundary, then the return value, then the requirement. No filler and every sentence carries distinct information.

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?

With no output schema, the description supplies the return value ("final state (killed)") and the survival boundary, which is what an agent most needs before calling it. It stops short of stating failure modes or whether in-flight output is lost, a minor gap for a destructive two-param tool.

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 both parameters carry descriptive text with patterns and origin references, so the schema does the heavy lifting. The description adds only an auth note ("Requires: token") that is not actually a declared parameter, adding no semantic detail about task_id or sandbox_id.

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 a running background task and all processes it started") and immediately scopes it against the adjacent sibling by clarifying "The sandbox itself keeps running," which separates it from kill_sandbox.

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?

The description gives clear context for when this applies (stopping a running background task) and implicitly rules out sandbox teardown, plus states the precondition "Requires: token." It does not, however, name an alternative tool explicitly or say what to do if the task is already finished.

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