skypilot_cluster_exec

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

Adds real behavioral context beyond annotations: it syncs the workdir, runs commands, and returns a request_id that must be polled via a named sibling. Annotations only say openWorld/destructive=false, so this async/polling contract is genuinely new info. Missing: what happens to existing cluster state or whether commands run detached.

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: what it does, what it does behaviorally (sync + run), and the return/poll contract. Front-loaded with the core action, no 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?

With an output schema present, the description need not explain return values, and its request_id/polling tip is a helpful extra. The two unexplained boolean params (down, dryrun) are the main gap given 0% schema coverage.

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% – four parameters are completely undocumented in the schema, so the description must compensate. It explains task_yaml (a SkyPilot task YAML string) but says nothing about cluster_name, down, or dryrun. Partial compensation only, hence baseline-ish 3.

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 (execute a task) and resource (an existing cluster), and distinguishes from launch/start siblings by 'existing cluster'. An agent can pick this out from skypilot_cluster_launch or skypilot_cluster_start without opening a 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?

Makes clear it operates on an *existing* cluster, implying you must have launched/started one first, and points to skypilot_get_request for polling. However it never states when NOT to use it (e.g. use cluster_launch for new clusters) nor mentions prerequisites explicitly.

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