kubernetes_manifest_review

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

Annotations already declare readOnly, idempotent, non-destructive and closed-world, so the safety profile is covered. The description adds a genuinely new behavioral fact — 'No cluster access' — telling the agent no credentials, live state, or fetch step are involved, which changes how the agent prepares input. It stops short of describing output shape or severity, but an output schema exists to carry that.

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?

Two sentences, zero filler. The checklist is front-loaded and each enumerated item maps to a real check the tool performs, while the scoping constraint ('No cluster access') is placed last as a clean boundary statement.

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 an output schema exists, return values need not be explained, and the annotations cover the safety profile. The remaining gap is audience guidance — e.g. which resource kinds are recognized and whether multi-document/bundle-wide checks (PDB and NetworkPolicy coverage) require all related manifests in a single call, which the agent must infer.

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 carry the load; it partially does by specifying 'parsed JSON objects', which disambiguates from raw YAML strings — the most likely caller error. It says nothing about the array bound (maxItems 300) or that a single-element array is valid, leaving the coverage gap only half closed.

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?

Uses a specific verb ('Review') with a specific resource ('Kubernetes manifests') and enumerates exactly what is inspected: probes, resources, security context, image pinning, host access, secrets in env, PDB and NetworkPolicy coverage. The Kubernetes-manifest domain cleanly separates it from sibling review tools like terraform_plan_review, cloudformation_review and iam_policy_review.

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 phrase 'No cluster access' usefully bounds the tool to static analysis of supplied objects, implying the caller must provide the manifests rather than a cluster reference. However, it never states when to prefer a different review tool, whether it applies to Helm/Kustomize output or only rendered manifests, or what prerequisites the input must satisfy.

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