hcloud_raw_request

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

Goes well beyond the annotations (destructive/openWorld) by disclosing auth behavior (configured API token is sent), retry semantics (429 retried; 5xx retried on non-POST methods), and deliberate omissions (no pagination, no action polling). Critically, it explains that HTTP errors return '{ status, body }' rather than an error result, which changes how the agent must interpret output.

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?

Four sentences, each carrying distinct, non-redundant information: escape-hatch scope first, then transport/retry behavior, then omissions, then the error shape. No padding or restatement of the title.

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 usefully defines the error return shape and the retry/pagination caveats, and the confirm-gate is covered by the schema. It stops short of stating what a successful response looks like (presumably the raw API JSON body), leaving one inference for the agent.

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 60%: path, body and confirm are documented in-schema, while method and query are not. The description adds indirect method semantics ('5xx on methods other than POST') but never explains path/query/body usage itself, so it neither compensates for the gap nor adds much over the schema.

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 ('issue an arbitrary request against the Hetzner Cloud API') and frames it explicitly as an 'Escape hatch'. Against ~150 dedicated sibling tools, the escape-hatch framing makes the distinction unmistakable.

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?

'Use only when no dedicated tool fits' is an explicit when-not rule pointed at the whole sibling set, which is the only practical way to reference alternatives at this scale. The agent knows to search for a dedicated tool first rather than reaching for this by default.

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