rbac_review

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

No annotations are supplied, so the description carries the full burden, and it does disclose what the analysis looks for and that it enumerates roles and subject bindings. However it never states that the operation is read-only/static, whether a live cluster or credentials are needed, or what happens on an invalid path — meaningful gaps for a file-consuming review tool.

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 purpose, then a compact rule list, then the secondary listing behavior — no filler sentences. The enumerated security checks are dense but each one maps to real detection content, though the run-on comma list is harder to scan than a short bulleted form would be.

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?

An output schema exists, so return-value explanation is not required, and the detection scope is well covered. What is missing is context an agent needs to call it correctly: what `path` points at, whether cluster access is required, and how it differs operationally from the sibling review tools.

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?

There is a single required parameter, `path`, with 0% schema description coverage, so the description must define it — but it never mentions the parameter at all. It is unclear whether `path` is a file, a directory of YAML manifests, or a Helm-rendered output root.

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?

Specific verb+resource ("Review RBAC") followed by a concrete enumeration of the eleven rule families checked (wildcard verbs, cluster-admin bindings, secret reads, escalate/bind/impersonate, pods/exec, nodes/proxy, anonymous/default-SA bindings). It also states the secondary output (listing Roles/ClusterRoles and their subjects), which clearly separates it from generic siblings like lint_manifests or check_references.

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?

Usage is only implied: an agent can infer it should call this when auditing RBAC manifests. There is no explicit when-to-use statement, no guidance on when to prefer lint_manifests or check_references instead, and no stated prerequisites (e.g. whether the path must be a manifest directory or a live-cluster kubeconfig).

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