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

Annotations only provide destructiveHint=true, and the description usefully adds cost behavior ('Snapshots are billed for the space they use') and timing guidance. It does not, however, reconcile the destructive annotation (e.g., that backups consume a backup slot) or explain side effects on the source server, so disclosure is partial beyond the annotation.

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, front-loaded sentences: purpose first, then the usage cue, then cost, then the API mapping. Each sentence earns its place with no filler or repetition.

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 three-parameter create tool with no output schema, the description covers purpose, timing, cost, and endpoint, which is enough to invoke it correctly. It is only slightly incomplete in not stating the outcome (e.g., that an image ID is produced / an action is returned) or failure 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% and the enum for type (snapshot vs backup, default snapshot) is already documented in the schema. The description adds no parameter-level syntax or format detail, so the baseline 3 applies.

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 and resource ('Create a snapshot image from a server's disk') and even maps it to the underlying API endpoint, so there is no ambiguity about what the tool produces. It is easily distinguished from read-oriented siblings like hetzner_get_server and from hetzner_create_server, which provisions rather than snapshots.

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 a clear contextual trigger: 'the safe thing to do BEFORE a risky change,' which tells the agent when this tool is appropriate. However, it never contrasts the snapshot path against the backup path (hetzner_enable_server_backup) or states any preconditions/exclusions, so routing guidance is context but not alternatives.

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