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

With no annotations supplied, the description carries the full burden. It does useful work by disclosing the check catalog, the 20-manifest ceiling, and that near-misses are reported ('with the nearest near-miss'), which implies diagnostic rather than pass/fail behavior. It never states whether the tool is read-only, what the result looks like, or how failures are surfaced, leaving real gaps for a mutation-adjacent pre-apply gate.

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 purpose is front-loaded, which is good, but the body is one very long sentence piling seven check types into a single clause chain. Worse, the text is cut off mid-word at 'ConfigMap/Se', so the definition is visibly incomplete and the reader cannot tell what the ConfigMap check actually covers.

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?

There is no output schema, so the description should at least sketch what a cross-check returns (violations, severity, near-miss suggestions), and it only gestures at near-misses. Combined with the truncated final clause, the definition is adequate to call the tool but not complete enough to predict its results.

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 100%, so both `manifests` and `closedWorld` are already fully documented in the schema, including the 20-item and 24,000-character limits. The description merely repeats the 'up to 20 manifests' constraint and says nothing about `closedWorld` or what unverified references mean in practice. Baseline 3 is correct.

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 (parses Kubernetes YAML manifests and cross-checks them against each other) and enumerates the exact reference pairs it validates: Service selectors vs pod template labels, targetPorts vs containerPort names, Deployment selectors, Ingress backends, ConfigMap references. No sibling in the list does manifest cross-referencing, so an agent can route here unambiguously.

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?

Gives a concrete usage context: 'for an agent that generated or edited manifests before kubectl apply', which tells the agent exactly when this is appropriate. It stops short of stating when not to use it or naming any alternative tool, so it misses the top band.

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