Retrieve available ISO images from Hetzner Cloud to mount during server creation or rebuild. Filter results by name or label selector to find the right image.
List ISOs. Read only.
| Name | Required | Description | Default |
|---|---|---|---|
| id | No | Fetch one by id. | |
| query | No | Filters, e.g. name, label_selector. | |
| verbose | No | Full payload. |
Changes observed during successful MCP inspections.
v0.7.0Input schema / properties / id / descriptionPrevious value: -"Optional resource id to fetch a single item."New value: +"Fetch one by id."Input schema / properties / query / additionalProperties / anyOfRemoved value: -[
- {
- "type": "string"
- },
- {
- "type": "number"
- },
- {
- "type": "boolean"
- }
-]Input schema / properties / query / additionalProperties / typeAdded value: +[
+ "string",
+ "number",
+ "boolean"
+]Input schema / properties / query / descriptionPrevious value: -"Optional query parameters such as name or label_selector."New value: +"Filters, e.g. name, label_selector."Input schema / properties / verbose / descriptionPrevious value: -"Return full payload instead of the compact view."New value: +"Full payload."v0.3.0Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations supplied, the description must carry the full behavioral burden, and "Read only" does disclose the single most important trait: this tool does not mutate state. It still omits return shape, pagination, and any permission or scoping notes, so the coverage is thin for a fully un-annotated tool.
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 totalling four words, with the resource identified first and the safety trait second. Nothing is padded and nothing is buried.
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?
There is no output schema and no annotations, so the description is the only place return behavior or filtering semantics could be explained, and it explains neither. The 100% schema coverage on parameters limits the damage, leaving the definition minimally viable rather than complete.
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 id, query, and verbose each documented in the schema itself, so the baseline of 3 applies. The description adds no syntax, example filters, or explanation of the nested query object beyond what the schema already states.
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?
"List ISOs" gives a clear verb plus resource, so an agent immediately knows this is a read of the ISO catalog. However, it offers no differentiation from adjacent siblings like cloud_list_images or cloud_list_volumes, leaving the agent to infer the distinction from the name 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?
The description says nothing about when to reach for this tool versus cloud_list_images or how the id/query parameters change its behavior. "Read only" is a safety note, not usage guidance, so the agent gets no when/when-not context.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.