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

Annotations already declare readOnlyHint=true, and the description goes further by disclosing freshness ('never answered from a cache') and concrete failure modes (agent unreachable, metrics-server not installed). That is substantive behavioral context beyond the annotation, though it stops short of detailing auth/rate-limit behavior.

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 core purpose and measurement source, then scoping, freshness/failure behavior, and the sibling disambiguation. Every sentence carries distinct information with no filler.

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?

No output schema exists, and the description adequately conveys the shape of results (per-pod rows, sortable, optional per-container breakdown) plus failure conditions and freshness. 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 coverage is 100%, so baseline would be 3, but the description adds semantic meaning not in the schema: that container values are summed by default and only broken out optionally, and that omitting the namespace reads every namespace. This maps directly onto include_containers and namespace semantics.

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?

The description names a specific verb and resource (live CPU/memory usage per pod) and states exactly how it is measured (metrics-server, summed over containers, optional breakdown). It explicitly distinguishes itself from the sibling get_pods, so an agent can pick it without opening either 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?

It gives explicit routing guidance: 'Use this to find what is actually consuming a node; get_pods shows requests and limits, not usage.' It also states the scoping choice ('filter to one namespace or read every namespace'), leaving no inference needed about when this tool is the right pick.

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