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

With only readOnlyHint=true in the annotations, the description carries the burden and delivers: read-only over SSH-via-bastion, 'Runs nothing that changes the cluster', and rich semantics for three-valued health ('unknown' must never be reported as down), health_source signal provenance, and the conservative failure_tolerance lower bound. This is behavioral context well beyond the annotations.

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?

Purpose and destination are front-loaded, and nearly every clause carries information. The cost is form: one very long run-on sentence with deeply nested parentheticals, which is harder to parse than it needs to be and could be broken into a short summary plus detail.

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?

No output schema exists, so the description must explain the return shape — and it does comprehensively (member ids in hex and decimal, URLs, learner flag, per-member health, alarms, quorum size, quorum_evidence, failure_tolerance, health_unknown_voting_members). Nothing needed to interpret or call the tool 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 coverage is 100%, so the baseline is 3, but the description adds operational meaning: node_id is preferred and sourced from list_cluster_nodes, the node must be a control-plane node, and a healthy peer should be chosen when one control-plane node is down because the inspection talks to that node's local etcd. That last point is real guidance the schema does not carry.

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 ('Inspect the etcd cluster membership') and nails down the mechanism (read-only inspection on one control-plane node over SSH-via-bastion) and the exact data returned (member list, health, alarms, quorum summary). It is unmistakable against siblings like remove_etcd_member or list_cluster_nodes.

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?

Explicit when-to-use: 'BEFORE touching a degraded control-plane node, to know the quorum margin; and before remove_etcd_member, to get the member id.' Adds a selection rule (pick a HEALTHY peer when one control-plane node is down) and explicit exclusions (not for imported or managed-Kubernetes clusters, nor Proxmox/HPE Morpheus).

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