stop

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

Annotations already declare destructiveHint=true and openWorldHint=true; the description adds genuinely new behavioral information that this is a cooperative ACPI-style request and never a forced power-off, which qualitatively changes how an agent should reason about the risk. It still omits whether the call blocks until shutdown completes, timeouts, and what happens to running workloads, so it is not fully transparent.

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 immediately qualified by the most important constraint ('Never forces power off'). Nothing is wasted or padded.

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?

For a zero-parameter tool with no output schema, the description covers the essential semantics of a graceful versus forced shutdown. It is only slightly short of complete because it does not say whether control returns immediately or after the guest actually stops, which matters for sequencing follow-up calls.

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?

The tool takes zero parameters, so the baseline of 4 applies. The description correctly implies no arguments are needed to trigger a guest shutdown.

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 gives a specific verb ('Request a graceful guest shutdown') and a clear resource (the guest), which is immediately distinguishable from the sibling 'start' and the observation tools like 'status'/'screenshot'. It stops short of naming a sibling explicitly, so it lands at 4 rather than 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?

Usage is only implied: an agent can infer this is the tool for shutting the guest down, but there is no statement of when to prefer it over other approaches, no prerequisite conditions, and no guidance on what to do if the graceful request is ignored. No exclusion or alternative is named.

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