power

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

Annotations already mark this as destructive and non-idempotent. The description goes far beyond that by disclosing approval gating, per-invocation confirmation, the honest effect report with verified true/false/null semantics, and invalidation of snapshot frame refs. This is rich, non-redundant behavioral context.

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?

Concise and well-structured: opens with a one-line purpose, then adds critical caveats (destructive, gating) and behavioral details. Every sentence carries distinct value with no repetition or filler. Dense but organized.

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 the tool's complexity (destructive, approval-gated, side-effectful), the description covers the essential operational context: how approval works, what the result indicates, and side effects on snapshots. It does not fully describe the return format or the exact semantics of off-hard vs reset, but the enumerated action values and partial result coverage make it largely complete for an agent.

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 compensate. It does explain the confirm parameter meaningfully (used for approval under standing policy). The action enum values are self-explanatory, but the profile parameter is left undocumented. The description partially compensates but not fully.

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+resource: "Change host power state." This clearly differentiates from sibling tools like power_state (read-only state inspection) and wake (power-on via network). The DESTRUCTIVE warning further reinforces the tool's intent.

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 clearly conveys that this tool is for changing power state, but it does not explicitly mention when to use it over alternatives or provide exclusions. Usage context is implied (change vs. read), but no direct comparison to power_state or other siblings is given.

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