cordon_node

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

Annotations already declare readOnlyHint=false, destructiveHint=true, idempotentHint=false, so the safety profile is covered structurally. The description usefully adds the [WRITE][risk=medium] tag, the precise semantic effect (no new pods land), and the dry-run escape hatch. It does not state what happens to already-running pods, which is a minor remaining gap.

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 operation, the inverse, and the dry-run hint before the Args block, so the highest-value information comes first. The dry_run explanation is stated twice (prose and Args), which is mild 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?

For a 3-parameter mutation with no output schema, the description covers purpose, argument meaning, preview behavior, and the reverse operation. The only omission is whether existing pods on the node are affected, which matters for an agent judging impact.

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 parameter meaning, and it documents all three: name (with a pointer to node_list), dry_run (preview semantics), and target (k8s target name from config). Coverage is complete, though target's meaning stays slightly abstract.

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?

State a specific verb+resource ('Mark a node unschedulable') with an immediate parenthetical clarifying the effect ('no new pods land'), and it explicitly names its inverse sibling uncordon_node. An agent can distinguish this from drain_node and uncordon_node without reading 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?

It names the reverse operation (uncordon_node) and gives a clear preview path ('Pass dry_run=True to preview without cordoning'). It stops short of stating when to prefer cordon over drain_node, so it lacks explicit exclusions, but the context for use is clear.

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