skypilot_ssh_down

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

Annotations already declare destructiveHint=true, so the tearing-down semantics are corroborated rather than contradicted. The description adds the ssh-target scoping and the request_id return, but says nothing about irreversibility, what happens to running work, or auth requirements – modest added context only.

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?

Two short sentences, front-loaded with the action and target, then the optional parameter and the return value. 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?

An output schema exists so the return value need not be explained beyond the request_id note, which it provides. However, with only one destructive action, no usage context, and no auth or side-effect detail, the definition remains thin for a cluster-teardown operation.

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% and the description at least explains what the single 'infra' parameter does ('Optionally specify a specific infra name') and that it is optional. That compensates meaningfully for the undocumented schema, though no format or naming-convention detail is given.

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 ('Tear down') and resource ('Kubernetes cluster on SSH targets'), which clearly distinguishes it from the parallel skypilot_cluster_down and skypilot_ssh_up siblings via the 'SSH targets' scope. It's specific but doesn't explicitly name a sibling it differs from, keeping it at a 4.

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 notes the optional infra name but gives no when-to-use context, no prerequisites, and no mention of the corresponding skypilot_ssh_up as the natural counterpart. An agent must infer the usage scenario from the name alone.

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