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

Annotations already declare readOnlyHint=true, so the safe-read profile is covered by structured data. The description adds only the upstream endpoint (GET /servers/{id}/metrics), a minor detail, and says nothing about rate limits, metric retention windows, default resolution, 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, both front-loaded: the capability first, the API mapping second. No filler and nothing an agent must scan past to find the purpose.

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 read-only fetch with a fully described input schema and no output schema, the description covers the essentials: what is returned, for which server, and over what window. It is slightly thin on what the time series actually contains (units, sample structure) and on default step behavior.

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%, so all five parameters (server_id, type, start, end, step) are already documented inline, including the type enum. The description's mention of 'CPU, disk or network' and 'over a window' only echoes what the schema states, establishing the baseline 3 rather than adding new semantics.

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 states a specific verb (Fetch) and resource (CPU, disk or network time series) scoped to a single server and a time window, which distinguishes it from close siblings like hetzner_get_server (metadata) or hetzner_list_servers. It does not explicitly name those siblings, so it stops short of a 5.

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?

Usage is only implied by the scope: an agent can infer this is the tool for historical metric data, but there is no explicit when-to-use, when-not-to-use, or named alternative (e.g. use hetzner_get_server for static attributes). No prerequisites or retention/cost caveats are given.

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