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

The destructiveHint annotation flags that this is a destructive action, but the description goes further and specifies exactly what is lost: 'Existing backups are DELETED.' That is the single most decision-relevant fact for this operation and is precisely the kind of detail annotations do not carry.

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?

Three short sentences, no filler, and the irreversible consequence is placed early where it can stop a wrong call. Every sentence carries information.

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 single-parameter action endpoint with no output schema, the description supplies the operation, its scope, its destructive consequence, and the underlying API route. Nothing an agent needs to invoke it safely is missing.

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% with a single required server_id, so the schema already documents the parameter fully. The description adds no format, range, or selection semantics beyond 'for a server,' which is the baseline 3 for schema-covered parameters.

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 precise verb ('Turn off') plus resource ('automatic backups for a server'), and the inverse relationship to hetzner_enable_server_backup is unambiguous from the wording. The added API endpoint removes any residual doubt about which operation this maps to.

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: an agent can infer this is used when backups are no longer wanted, and the data-loss warning implicitly signals caution. It never names the counterpart tool (hetzner_enable_server_backup) or states prerequisites/exclusions, so no explicit when/when-not guidance is given.

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