get_kubernetes_costs

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

The description mentions requirements (pip install finops-mcp[kubernetes]) and optional metrics-server for actual CPU/memory data, but does not disclose whether the operation is read-only, its cost implications, or side effects. No annotations are provided, so the description should carry the full burden of behavioral disclosure, which is insufficient.

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?

The description is concise, uses a clear structure with a main statement, requirements section, and examples list. It is front-loaded with the purpose and has no redundant information.

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 covers the primary use cases with examples, but lacks details on output format, error handling, or performance considerations. Given no output schema and low parameter coverage, more context would be helpful.

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?

The input schema has two optional parameters (context and namespace) with schema description coverage at 0%. The description does not explain the parameters or how to use them. The examples imply namespace usage but do not clarify the context parameter.

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 it provides a full Kubernetes cost breakdown, including node costs attributed to namespaces, workloads, and labels, and detects wasted spend and rightsizing opportunities. This distinguishes it from sibling tools like get_kubernetes_cost_trends or get_kubernetes_namespace_breakdown.

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 provides five example queries that illustrate when to use this tool, covering cluster cost, namespace spend, waste, over-provisioned pods, and CPU efficiency. However, it does not explicitly advise when not to use it or compare to alternatives.

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