pod_top

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

Annotations only declare readOnlyHint=true, so the description adds real value: it discloses the metrics-server dependency and the failure mode (returns available: False with a clear message). That is exactly the kind of context annotations cannot provide; it stops short of detailing return fields or rate limits.

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 a bracketed read tag and the one-line purpose, followed by the failure behavior and a compact args block. Every sentence carries load and nothing is padded.

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 correctly notes the notable return case (available: False when metrics-server is absent). Combined with full parameter coverage and the readOnly annotation, an agent has enough to call it; only return-field detail and sibling routing are missing.

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 both parameters, and it does: namespace with its omit-semantics and target as the config target name. This meaningfully compensates for the empty schema, though 'target' is described a bit thinly.

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?

It states a specific verb+resource combination: per-pod CPU/memory usage. 'Per pod' implicitly distinguishes it from the sibling node_top, though it never names an alternative. The purpose is unmistakable to an agent.

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 description gives a precondition (metrics-server required) and parameter context (omit namespace for all namespaces), which implies usage. But it never says when to choose this over pod_describe, pod_health_rca, or node_top, leaving comparison to inference.

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