pod_health_rca

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

readOnlyHint already covers safety, but the description adds real value beyond annotations: it discloses the worst-first ordering and that each finding cites the triggering reason string/restart count plus a concrete kubectl action. No mention of rate limits or permissions, but the output-shape disclosure is a meaningful addition.

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 [READ] tag and the scan scope, then the return shape, then args. Efficient overall, with only minor redundancy between 'Omit namespace to scan all' and the namespace arg line restating the same rule.

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 still explains the return shape (worst-first findings with reason strings and suggested actions), all three optional params, and the scoping behavior. An agent has everything needed to call it correctly.

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 does so: namespace is explained with its omit-for-all behavior, label_selector gets a concrete example ("app=web"), and target is explained as a config name defaulting to the default. All three params are covered, though no format details for target values are given.

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 (scan) and resource (pods) plus the exact failure modes it targets (CrashLoopBackOff, image-pull failures, OOMKilled, unschedulable Pending, high restarts). This clearly separates it from pod_list, pod_describe, and workload_readiness_rca without opening any schema.

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?

Tells the agent when to reach for it (diagnosing broken pods) and gives the scoping rule 'Omit namespace to scan all.' It does not explicitly name alternatives such as pod_describe or pod_logs or state when-not to use it, so it lands just short of full routing guidance.

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