cluster_health

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

The annotations already carry readOnlyHint=true and destructiveHint=false, so the description does not need to re-state safety. It, however, adds a description of what the snapshot covers, which is a small value-add. It does not mention any potential cost or latency difference between cluster-only and per-index mode, so a 3 feels right in light of the annotation safety coverage.

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 sentences, front-loaded with the data fields, with the troubleshooting routing at the end. There is no filler or unnecessary repetition, making it easy for an agent to parse.

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?

For a simple two-parameter, all-optional, read-only tool with an output schema, this description covers the relevant surface area: what the health summary includes, how granularity can go per-index, and when it should be used. The only missing piece is more structured parameter wording, so it's close to complete but not perfect.

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 0%, so the description must compensate for the two parameter names. It gives a weak hint for the level param by saying 'optionally' per-index health, but it still doesn't explain valid values for level and does not describe include_nodes at all. Without valuable parameter detail, score remains low.

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?

The description clearly identifies the tool as a cluster-health snapshot and enumerates the specific data points it reports — status, node counts, shard states, pending tasks, and optional per-index health. It does not explicitly contrast itself with sibling tools like index_health or cat_nodes, so a top score feels too generous.

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?

The clustering of 'Start troubleshooting here' gives agents a clear behavioral directive: begin diagnosis with this tool. It also signals that per-index health is an optional add-on. Missing is explicit guidance about when to prefer index_health or cat_nodes, but the intended default path is clear enough.

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