vm_power_off

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

With no annotations, the description discloses that it is a write operation with medium risk, reversible via power-on, and includes a dry-run mode with a self-lockout guard. However, it does not mention potential data loss from hard power-off.

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?

The description is very concise with a clear structure: header indicating risk, action statement, and parameter list. Every sentence adds value without redundancy.

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?

Given no annotations, output schema, or high complexity, the description adequately covers the action, parameters, and key behavioral notes (reversibility, dry_run guard). Minor gaps include lack of return value or error state info, but acceptable for a simple 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?

All three parameters (vm_ext_id, dry_run, target) are explained in the Args section, adding meaning beyond the schema. vm_ext_id source is clarified, dry_run purpose with self-lockout is detailed, and target defaults explained. Schema coverage is 0% so description fully compensates.

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?

The description clearly states it performs a 'hard power off' on a VM, using a specific verb and resource. It also notes reversibility, differentiating it from potentially destructive actions. Despite not explicitly naming siblings, the action is distinct.

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 implies usage for forced power-off scenarios but lacks explicit guidance on when to prefer this over graceful shutdown (vm_guest_shutdown) or reboot (vm_reboot). No when-not or alternative suggestions are provided.

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