list_resourceList Kubernetes resources of any kind, including CRDs, through read-only queries. Blocked resource kinds are refused to ensure safe inspection.
List resources of any kind (including CRDs) via the dynamic client. GET/LIST only; never mutates. Blocked kinds (see config.toml) are refused.
| Name | Required | Description | Default |
|---|---|---|---|
| kind | Yes | ||
| namespace | No | ||
| api_version | No | v1 | |
| field_selector | No | ||
| label_selector | No |
Changes observed during successful MCP inspections.
v0.1.0Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint, idempotentHint, and destructiveHint, so the description's 'never mutates' mostly reinforces them. It adds valuable non-obvious behavior: blocked kinds listed in config.toml are refused, and the dynamic-client mechanism is disclosed. No contradiction with annotations.
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 terse sentences, each earning its place: the first states the action and scope, the second guarantees no mutation, and the third warns about blocked kinds. The most decision-relevant information is front-loaded.
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 generic read-only list tool, the description covers core purpose, safety, and the blocked-kind failure mode. However, there is no output schema, no mention of return shape or pagination, and no guidance on selector syntax or setting api_version for CRDs, leaving moderate gaps.
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 0%, so the description must compensate for the five parameters, but it only indirectly supports 'kind' via 'any kind'. Nothing explains api_version, namespace, field_selector, or label_selector semantics, leaving the agent to infer meaning from parameter names alone.
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 ('List'), a resource scope ('resources of any kind including CRDs'), and the mechanism ('dynamic client'), making it clearly distinct from specialized siblings like list_pods and list_deployments. The GET/LIST-only qualifier further pins down behavior.
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 implies when to use it: any resource kind, including CRDs, that sibling list tools do not cover. However, it does not explicitly name alternatives or state when not to use it, and 'Blocked kinds are refused' is the only direct usage constraint.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.