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

Annotations already declare destructiveHint=true, idempotentHint=true, readOnlyHint=false, so the safety profile is covered. The description adds genuinely new behavioral context: the kill cascades to all child processes started by the task, the final state is returned as 'killed', and the surrounding sandbox survives. Only the auth requirement and return surface are lightly covered.

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?

Four short, declarative sentences with zero waste, and the primary action is front-loaded before the scope caveat and the return/requirement notes. Every sentence carries information the agent needs.

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 present, the description compensates by stating the returned final state ('killed'), and it clarifies the blast radius (child processes) and the non-effect on the sandbox. For a two-parameter mutation with full annotation coverage, nothing essential 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 description coverage is 100%, so task_id and sandbox_id are already fully documented with their id formats and provenance. The description adds nothing parameter-specific, so the baseline of 3 is appropriate.

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 (Stop) and resource (a running background task and all processes it started), and explicitly narrows scope with 'The sandbox itself keeps running', which distinguishes it from the sibling kill_sandbox. An agent can tell what it does and what it does not do without opening the 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?

Context is implied: this is the per-task stop operation, contrasted implicitly against kill_sandbox by the 'sandbox keeps running' note. However, it never says when to prefer this over get_task, cancel_service, or kill_sandbox, and lists no prerequisites beyond the auth token. Usage is inferable but not stated.

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