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

The readOnlyHint annotation is confirmed ('Read-only'), and the description adds genuinely non-derivable behavior: it reaches the host over SSH rather than through the cluster agent because the agent sits behind the bastion, and it categorically cannot succeed while the bastion is offline. It also discloses the correct pre-check tool that avoids touching the host. This is well beyond what the annotation provides.

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 inspected surfaces are front-loaded in the first sentence, then each subsequent sentence carries a distinct payload: read-only assurance, trigger conditions, sibling exclusion, transport mechanism, failure mode plus prerequisite, and the power-action alternative. No sentence is redundant despite the length.

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 a single fully documented parameter, no output schema, and only a readOnlyHint annotation, the description compensates by enumerating what will be inspected (effectively the return content), stating the transport path, the offline failure condition, and the required prerequisite. An agent has everything needed to call it correctly and in the right order.

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?

Only one parameter (cluster_id) and schema description coverage is 100%, so the schema already documents the UUID format and points to list_clusters for discovery. The description adds no additional parameter-level meaning, so the baseline 3 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 precise verb (inspect) and resource (the SSH bastion host of an Ankra-provisioned cluster) and enumerates the specific surfaces examined: sshd config, failed-login volume, disk, systemd units, journal errors, listening ports, pending security updates. It explicitly distinguishes itself from the nearest sibling by noting the bastion runs no kubelet so ssh_diagnose_node cannot inspect it.

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 triggers ('after a bastion outage', 'asked about the bastion's security posture'), names the excluded alternative (ssh_diagnose_node) with the reason it does not apply, states the prerequisite (call get_bastion_health first, which does not touch the host), and routes the power action to restart_node with target="bastion". Nothing about tool selection is left to inference.

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