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

Annotations supply only destructiveHint=true, so the description carries most of the burden and delivers real value: it discloses the ACPI/graceful mechanism, the preference ordering against hard power-off, the billing consequence of a stopped-but-existing server, and the underlying API call. It omits that the operation is asynchronous and typically returns an action to poll via get_action.

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?

Three tight sentences, front-loaded with the action and mechanism before the preference and the cost caveat; every sentence carries information. The trailing raw endpoint string is marginally useful for debugging but is the least essential part.

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 single-parameter mutation with no output schema, the description covers mechanism, safety posture, and cost consequences well. The missing piece is post-call behavior — that shutdown is asynchronous and the server may take time to actually stop, which an agent needs to set expectations.

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?

One parameter with 100% schema description coverage ('The server to shut down.'), so the schema already fully documents the input. The description adds no id format, ownership, or validation detail beyond that, which is the expected baseline when coverage is complete.

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 mechanism — 'Ask the guest OS to shut down gracefully via ACPI' — which is far more precise than the title 'Shut down a server'. It contrasts with a hard power-off, though it does not name a sibling tool (reboot_server, poweron_server) to anchor the distinction.

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?

'Prefer this over a hard power-off' gives a clear selection rule for the graceful-vs-forceful choice, and the cost note hints at when stopping is insufficient (deleting is required to stop billing). No explicit exclusions relative to siblings like reboot_server or poweron_server are given.

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