vm_power

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

Annotations already declare destructiveHint=true and readOnlyHint=false; the description goes beyond them by distinguishing graceful shutdown from forced turn_off/reset and by disclosing the confirm_vm guard and the ALLOW_POWER/allowlist gating. It does not say what unsaved state is lost on turn_off/reset or whether pause requires a running VM, which is the remaining gap for a destructive mutation tool.

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 sentences, no filler, and the destructive-action guard plus auth requirement are front-loaded right after the action list where an agent will see them before calling. Every clause carries information the schema does not.

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 return values need no explanation, and the description covers the risky path (forced power-off/reset) and auth gating. It stops short of stating per-action preconditions or whether the operation blocks until the VM settles, which matters for a multi-action power tool with an associated vm_wait sibling.

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 0%, so the description must carry the parameter load, and it does explain the non-obvious one: confirm_vm must equal vm_name and is required for turn_off/reset. It also implicitly mirrors the action enum. vm_name's expected format (name vs. ID) is never clarified, which is the only real omission.

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 opens with a full enumeration of the concrete state operations (start, graceful shutdown, save, pause, resume, forced power-off, reset) applied to a named resource, so the verb+resource pairing is unambiguous. It is clearly distinguishable from siblings like vm_list, vm_get, or vm_wait, which read state rather than mutate it.

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?

It names the preconditions required to call it (ALLOW_POWER permission plus allowlist membership) and the special guard for turn_off/reset, which is real routing guidance. There is no explicit statement of when to prefer this over siblings or which action to choose for a given VM state, so it stops short of fully prescriptive usage.

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