top_resources

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

Annotations already declare readOnlyHint=true, and the description adds rich behavioral context: returns live metrics, includes pod status, readiness, restarts, etc., and explains ranking behavior. No contradictions.

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 and well-structured: it starts with usage conditions, explains the output, details the three kinds, and ends with a usage reminder. Every sentence adds value without redundancy.

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?

Given no output schema, the description provides sufficient context about return values (live metrics with Kubernetes context). It covers all key aspects for a read-only ranking tool, though it could explicitly mention the output format.

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 coverage is 100%, but the description adds valuable context for the 'kind' parameter (explains aggregation for workloads) and the 'namespace' parameter (notes restriction for namespace-limited users). This goes beyond the schema descriptions.

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 the tool's purpose: investigating high CPU, memory pressure, OOMKills, etc. It specifies the action ('returns live metrics ranked') and the resource types (pods, workloads, nodes), distinguishing it from siblings.

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 explicitly states when to use the tool ('when investigating high CPU, memory pressure...') and advises using it before reading logs for relevant symptoms. It indirectly indicates when not to use it (e.g., not for logs), but does not explicitly name alternatives, which would raise the score to 5.

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