Cluster health check

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

Annotations already establish readOnly, idempotent, non-destructive and closed-world, so the safety profile needs no restating. The description adds behavior beyond that: findings are sorted worst-first and each carries a concrete recommendation, which tells the agent what the response looks like and how to act on it. No cost or latency/scope limitations are mentioned.

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?

Two short sentences, front-loaded with the check list and immediately followed by the routing cue. No filler and nothing buried.

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?

Zero parameters, rich annotations, and an output schema all carry the structural burden, so the description only needed to state scope and result shape. It does both, including ordering and the presence of recommendations, which is sufficient for an agent to invoke it confidently.

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?

The tool takes zero parameters, so there is nothing for the description to disambiguate; baseline 4 applies. The description correctly makes no parameter claims.

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?

Specific verb (check) plus an enumerated resource set: quorum, node availability, CPU/memory pressure, storage fill, HA. An agent knows exactly what the tool inspects. It stops short of distinguishing itself from siblings like ceph_health and storage_health, which overlap on 'storage fill levels', so the boundary is left implicit.

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?

'Start here for any "is something wrong with the cluster?" question' gives clear entry-point guidance and situational context. It does not name when to prefer ceph_health or storage_health instead, so the alternative-routing half of the guideline is missing.

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