check_services

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

Annotations only declare readOnlyHint=true; the description adds the important behavioral facts that it returns overall state plus failed units and that the call is refused for a non-running guest. It does not cover cost, latency, or result formatting, but that is minor for a single-guest state read.

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?

The purpose and return values are front-loaded, followed by usage and the running precondition, with no wasted sentences. The standalone 'Read-only.' sentence repeats the readOnlyHint annotation but is short enough to be harmless.

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?

With no output schema, the description still explains what comes back (overall state and failed units) and covers the main failure mode (guest not running). For a single-parameter read tool, an agent has everything needed to call it correctly and interpret the result.

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 the vmid parameter is already documented in the schema with a Proxmox VMID example and a pointer to list_guests. The description only reinforces 'one guest' and adds no syntax or format detail beyond the schema, so the baseline of 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 and resource ('systemd state of one guest') and names exactly what is returned: overall state (running, degraded, ...) and failed units. It is clearly distinguishable from siblings like apply_updates and reboot_guest, which only compare state internally.

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?

Gives explicit use cases ('before an update or when the user reports a problem') and names the alternatives that already perform the check themselves. It also states the exclusion condition: refused for a guest that is not running, with list_guests named as the way to check status.

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