get_resourceFetch any Kubernetes resource by name, including custom resources, with a read-only dynamic client. Blocked resource kinds are refused before API access.
Get a single resource of any kind (including CRDs) by name via the dynamic client. GET only; never mutates. Blocked kinds are refused.
| Name | Required | Description | Default |
|---|---|---|---|
| kind | Yes | ||
| name | Yes | ||
| namespace | No | ||
| api_version | No | v1 |
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. The description adds useful behavioral context beyond annotations by explicitly stating 'GET only; never mutates' and revealing that 'Blocked kinds are refused.' This gives the agent a clearer safety and failure profile.
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 with no filler. The core purpose is front-loaded, and each additional sentence ('GET only', 'Blocked kinds are refused') adds meaningful operational context.
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?
The description is adequate for a simple read-only getter, but gaps remain: it does not describe return values, provide any list or explanation of blocked kinds, or clarify how api_version and namespace are used. Since there is no output schema, some of this burden falls on the description.
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 documenting parameters. It mentions 'by name' and 'any kind', which loosely maps to the name and kind parameters, but it does not explain namespace or api_version semantics or their defaults. This is a significant gap for a generic dynamic-client tool.
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 clearly states a specific action ('Get a single resource'), the resource scope ('any kind including CRDs'), and the mechanism ('by name via the dynamic client'). This distinguishes it from sibling list/get-log tools without needing to inspect their schemas.
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 makes the use case clear: retrieve one known resource by name as opposed to listing resources or fetching logs. It does not explicitly name alternatives or provide when-not-to-use conditions, but its context is specific enough to route an agent correctly.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.