Retrieve subnets from Hetzner Robot dedicated servers. Filter by name or label selector, fetch one by ID, or request full payload details.
List subnets. 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?
No annotations are provided, so the description carries the full behavioral burden, and 'Read only' merely restates what 'List' already implies. It says nothing about auth requirements, whether query filters on nested objects are combinable, pagination, or result limits.
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 with no wasted prose, and the operation is front-loaded. But the second sentence ('Read only.') is redundant with the first and the overall brevity stems from under-specification rather than tight writing.
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 tool with three parameters including a nested filter object, no output schema, and no annotations, the description is too thin. It does not explain how the id path differs from the query path, nor what verbose changes about the response.
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 the schema already documents id, query, and verbose (including 'name, label_selector' examples). The description adds no syntax, format, or interaction detail beyond that, warranting the baseline 3 rather than more.
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 clear verb+resource ('List subnets'), so the core operation is identifiable. However, it gives no scope, return shape, or relation to near-neighbors like robot_list_vswitches or robot_list_ips, so an agent cannot tell from the description alone how this differs from the other robot_list_* tools.
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?
'Read only' is a property, not guidance on when to use this tool versus alternatives such as robot_list_vswitches (whose subnets these may be). There is no context, no prerequisite, and no pointer to a sibling tool.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.