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

Annotations already declare destructiveHint=true, but the description adds consequences that annotations cannot convey: running applications are terminated, remote connectivity is severed, and local physical power-on may be required to reconnect. That last point is critical decision-making information for an agent acting remotely and is not derivable from any structured field.

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, front-loaded with the authorization precondition, then the irreversible consequence. Every clause earns its place with 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 return values need no explanation, and the schema fully covers both parameters. What remains for the description — authorization requirement and the risk of losing remote access permanently — is stated explicitly.

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 100% and both parameters (device, delay_seconds with its 90s cap and rationale) are fully documented inline, so the description carries no additional burden. It adds no parameter meaning of its own, making the baseline 3 correct.

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 ("shut down the paired computer"), which is clearly distinct from the restart/sleep/lock power siblings by the verb alone. It does not explicitly name an alternative, so it stops 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?

"when explicitly authorized" gives a clear gating precondition for invoking a destructive action, which is exactly the context an agent needs. It never contrasts with power_restart, power_sleep, or power_lock, so the when-not guidance is absent.

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