hcloud_get_server_metrics_raw

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

Annotations already declare the operation read-only and non-destructive, but the description goes much further: it discloses the 30-day retention window, the automatic step adjustment targeting 200 samples, the hard 500-sample ceiling, and the non-obvious CPU normalization per-vCPU semantics. These are exactly the traits an agent needs to interpret results correctly and cannot be inferred from structured fields.

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 layout is well front-loaded — purpose, required type argument, then a scannable table of timeseries, then constraints. The opening two lines ('Get Metrics for a Server' / 'Get Metrics for specified Server.') are redundant, a minor waste in an otherwise efficient document.

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 correctly carries the burden of explaining the returned timeseries and units, and it does so thoroughly. The remaining gap is that no return envelope shape is described and the 'raw' distinction from the sibling is never addressed, which matters for a tool whose name implies a specific response format.

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%, so baseline would be 3, but the description adds genuine meaning: the type table maps each enum value to concrete timeseries names and units, and it explains how step behaves when omitted or when the sample cap forces adjustment. It does not clarify the start/end RFC3339 interaction with the 30-day window, keeping it from a 5.

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 ('Get Metrics for a Server') and enumerates the metric types returned, which makes the operation clear. However, it never distinguishes this from the sibling hcloud_get_server_metrics, nor does it explain what 'raw' means in this context, so an agent cannot confidently choose between the two from the description alone.

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 useful operating guidance — the type must be specified, multiple types can be comma-separated, metrics only cover the last 30 days, and step is auto-adjusted if omitted. What is missing is selection guidance: when to use this raw variant versus hcloud_get_server_metrics or hcloud_get_load_balancer_metrics, which is the primary routing decision an agent faces here.

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