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

Annotations only supply destructiveHint=true, so the description usefully adds the ACPI/graceful nature, the preference ordering, and the cost consequence (a stopped server still bills; only deletion stops it). It omits that the action is asynchronous and returns an action object, but the cost and mechanism disclosures are meaningful value beyond the annotation.

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 short sentences, front-loaded with the core action and mechanism, then preference, then the non-obvious cost caveat. Every sentence earns its place and nothing is 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 one-parameter action tool with a destructive annotation, the description covers what happens, how, why to prefer it, and the billing implication. The remaining gap is that no output schema exists yet the return value (an async action object) is not described, which is a minor omission.

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 100% and there is a single well-documented required parameter, so the schema carries the parameter semantics. The description adds nothing about server_id beyond what the schema says; baseline 3 applies.

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 (shut down a server) and the exact mechanism (graceful ACPI request to the guest OS). This cleanly distinguishes it from siblings like hetzner_poweron_server and hetzner_reboot_server without the agent needing to open either schema.

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 criterion and implies the when-to-use condition. However, it never names the competing sibling tools (reboot vs. shutdown vs. poweroff) or states when-not to use it, so it stops short of full routing guidance.

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