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

Annotations already declare readOnlyHint=true and openWorldHint=true, so the safety profile is covered. The description adds useful behavioral context that the measurements are external to the machine and requires vms.read, but it does not explain timeframe aggregation, defaults, sampling, or response shape.

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 returned metric categories and followed by the permission scope. There is no wasted wording.

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 simple two-parameter read-only metrics tool, the description gives enough to understand what is returned and the permission requirement. However, with no output schema it should clarify the timeframe behavior and the shape of returned metrics, which are currently left implicit.

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 only 50%: the `vm` parameter is documented as a machine id, but the `timeframe` enum has no descriptive semantics. The description mentions metric categories but adds nothing about how timeframe affects results or what the default is, so it does not compensate for the schema gap.

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 specifies the metrics returned (CPU, memory, disk, network) and that they are measured from outside the machine, which distinguishes it from guest-level or sibling metrics tools such as get_database_metrics. It does not use an explicit verb, relying partly on the tool name/title, so it is clear but not maximally self-contained.

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?

It gives the required permission scope ('vms.read') but provides no guidance on when to choose this tool versus get_vm, get_vm_network, or other metrics tools. Usage is only implied by the metric categories.

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