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

Annotations declare readOnlyHint=true and the description reinforces it ('Runs nothing that changes the node', 'read-only diagnostics snapshot') while adding substantial behavioral context beyond the annotation: exact snapshot contents, the path_diagnosis hop-failure/error-class model when SSH is unreachable, and the Hetzner-only firewall_inspection detail. This is far richer than the annotation alone.

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?

A single dense paragraph, but it is front-loaded with the core purpose and organized by concern (what it targets, what it returns, unreachable-node behavior, Hetzner specifics, constraints). Long, but nearly every clause carries decision-relevant information.

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 fully carries the return burden: it enumerates the snapshot fields, the path_diagnosis structure with cause classes, and the optional firewall_inspection. Combined with coverage of constraints and alternatives, an agent has everything needed to invoke and interpret it.

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 schema already documents all four parameters; the description's node_id/node_name guidance largely restates the schema ('preferred, from list_cluster_nodes'). It adds only the routing hint that the bastion node should use diagnose_bastion, which is minor relative to the schema baseline.

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 (diagnose) and resource (one Kubernetes node at the OS level over SSH-via-bastion), and precisely scopes what it targets: failures below the Kubernetes layer such as NotReady nodes, ssh_unreachable reconciliation, and crash-looping k3s/kubelet. It explicitly distinguishes itself from kubectl-style tools and from diagnose_bastion, so an agent can route 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?

Gives explicit when-to-use (OS-level failures invisible to kubectl), when-not (bastion/gateway has no kubelet - use diagnose_bastion; not for imported/managed clusters or Proxmox/HPE Morpheus), and ordering ('Use this before ssh_repair_node'). Alternatives and exclusions are named directly.

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