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

Annotations only give the safety triad (readOnly=false, idempotent=false, destructive=false); the description carries the real behavioral burden. It discloses that running pods are NOT evicted, that PodDisruptionBudgets are NOT consulted by delete_pod, that unknown nodes are refused with no side effects, and that the operation is fully reversible via uncordon_node.

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?

The action and its effect are front-loaded in the first sentence, and the operational guidance is logically ordered (effect, reversibility, workflow context, caveats, error behavior). It is on the long side and a sentence or two of the consolidation narrative could be trimmed without losing correctness.

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?

For a mutating tool with no annotations backing and no output schema, the description covers everything an agent needs: effect, non-eviction of pods, reversibility, prerequisite lookup via get_nodes, error handling for unknown nodes, and the PDB caveat for the follow-on delete_pod step.

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 the baseline is 3, but the description adds real meaning beyond it: node_name must match the Kubernetes node name exactly, get_nodes should be called to list them, and unknown nodes are refused without changes. It adds nothing extra for cluster_id or dry_run, which the schema already documents.

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 the exact verb and resource ('Cordon one Kubernetes node') and immediately defines the mechanism ('set spec.unschedulable=true so no new pods schedule onto it'), which is specific enough to distinguish it from sibling mutations.

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 frames the tool as 'the standard first step of node consolidation' and names the surrounding workflow (remove pods, let autoscaler reap the node). It also routes the agent to alternatives and exclusions: uncordon_node for reversal, delete_pod for pod removal, and it notes patch_resource refuses the Node kind.

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