pod_describe

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

readOnlyHint=true already establishes the safety profile, so the description only needs to add context. The [READ] tag and the enumeration of returned sections add modest value, but nothing about permissions, output volume, or truncation is disclosed.

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?

Front-loaded with the purpose and the diagnostic use case, then a compact Args block. Every line earns its place, with only the bracketed [READ] marker being slightly redundant given the annotation.

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?

With no output schema, the description compensates by listing the returned sections and the scenarios it serves, and all three params are addressed. It is adequate for a read-only single-resource tool, though multi-namespace or error behavior is unstated.

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 carries the full burden, and it does add real meaning: namespace omission defaults to the target's namespace, name points at pod_list for discovery, and target is tied to config. "target" is still vague about how a multi-cluster target is chosen.

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 specific verb and resource plus the payload it returns (status, conditions, container states, recent events), which is more concrete than most describe tools. It does not distinguish itself from the nearby pod_get or pod_health_rca siblings, so an agent still has to infer the boundary.

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 fastest single call to diagnose why a pod is not Ready (CrashLoopBackOff, ImagePullBackOff, scheduling failures)" gives a clear triggering situation and frames it against slower multi-call alternatives. It stops short of naming the competing tools (pod_get, pod_health_rca) or stating when not to use it.

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