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

Beyond readOnlyHint=true, it discloses freshness semantics ('never answered from a cache, always a fresh measurement') and failure conditions ('fails when the agent is unreachable or metrics-server is not installed'). This is high-value behavioral context an agent cannot get from the annotation or schema.

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 what it returns, followed by freshness/failure behavior and then usage routing. Every sentence adds distinct information with no redundancy.

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 readOnlyHint covering safety, a 100% schema, and no output schema needed, the description supplies purpose, data contents, freshness, failure modes, and sibling routing. Nothing an agent needs to invoke it correctly is 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 100%, including limit, sort_by enum, and the optional cluster_id/cluster_name, so the schema already documents all four parameters with defaults and enum meaning. The description adds no parameter-level detail, so the baseline 3 applies.

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+resource ('Live CPU and memory usage per node') with the data source (metrics-server) and the exact contents returned (allocatable capacity + percentage in use). It also names a sibling it is not (get_cluster_status is only cluster-wide), so the agent can distinguish it without opening a 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?

Explicitly states when to use it ('prove resource pressure before scaling') and names the alternative it is contrasted against ('get_cluster_status only gives cluster-wide percentages'). The when-vs-alternative condition is fully specified.

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