skypilot_cluster_start

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

Annotations already declare destructiveHint=false and openWorldHint=true, so the safety profile is covered. The description adds useful behavioral context ('Reattaches preserved disks'), but says nothing about what force, down, or retry_until_up do to the restart semantics.

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 with the core action front-loaded and no filler. Efficient, though the middle 'reattaches disks' detail could be folded in more economically.

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?

An output schema exists, so the return value needn't be explained. But for a 6-parameter mutation with 0% schema coverage, omitting force, down, retry_until_up, and idle_minutes_to_autostop leaves the agent unable to invoke it correctly for non-default cases.

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%, so the description must carry the burden, yet it documents only wait_for (including its 'jobs_and_ssh'/'jobs'/'none' values). Five of six parameters — down, force, retry_until_up, idle_minutes_to_autostop, cluster_name — are given no meaning beyond their names.

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 ('Restart a previously stopped cluster'), and the qualifier 'previously stopped' implicitly distinguishes it from skypilot_cluster_launch (new cluster) and skypilot_cluster_stop. It never names a sibling explicitly, so it falls short of a 5.

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?

'Previously stopped cluster' implies the precondition for use, and the wait_for sentence gives conditional guidance for one parameter. However, there is no explicit when-not or named alternative among the many cluster siblings (launch, stop, down, autostop).

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