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

Annotations only declare readOnlyHint, and the description adds substantial context beyond that: availability limits (imported/managed clusters unsupported), the varying is_bastion_or_gateway flag semantics, and how per-node kubernetes_version reveals version skew. This is real operational disclosure, not a restatement of the annotation.

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 verb and resource are front-loaded in the first clause, and every subsequent clause carries information (returned fields, downstream use, exclusions). It is dense but not padded; only a slightly long first sentence keeps it from a 5.

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 compensates by enumerating the returned node fields and their meaning, and it documents the critical availability caveats. An agent has everything needed to decide, call, and interpret this tool.

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%, so both cluster_id and cluster_name are already documented as optional identifiers. The description adds no additional parameter semantics, so the baseline 3 for fully-covered schemas 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 ('List the provisioned VM nodes of an Ankra-managed cluster'), enumerates the exact fields returned, and scopes it to specific providers. It also distinguishes itself from sibling reads by clarifying it covers control-plane, worker, and bastion/gateway nodes rather than Kubernetes objects.

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?

Gives explicit usage context ('Use this before restart_node to find the exact node to target') and explicit when-not conditions (not available for imported or managed-Kubernetes clusters). It does not, however, contrast itself with the adjacent sibling get_nodes, leaving some ambiguity about which node-listing tool to pick.

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