get_cluster_query_vitals

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

Beyond readOnlyHint=true, the description discloses the endpoint called (GET /admin/vitals), the ro_admin RBAC requirement with a candid caveat that privilege requirements are undocumented, the Capella rejection path, and that results are per-node rather than cluster-wide. It also explains partial-failure semantics (unreachable_nodes omitted when all nodes answer) and the all-fail error case. Slight deduction only because failure behavior for a mid-call timeout is not spelled out.

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?

Front-loads purpose, then differentiation, usage trigger, preconditions, per-node behavior, and return shape — a logical progression with no filler paragraphs. Some sentences (the RBAC hedging parenthetical) are longer than needed, and the return-shape example partially duplicates the output schema.

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 fan-out diagnostic tool it covers everything an agent needs: what it measures, when to call it, environment and role limits, per-node keying by host:port, and both partial and total failure outcomes. Even with an output schema present, the inline return description adds useful shape context.

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% and the single parameter (timeout, default 30) is never mentioned in the description. It is unclear whether the timeout is in seconds, applies per node or to the whole fan-out, and whether it is per-request or total. The description therefore does not compensate for the schema gap, though the parameter is at least intuitively named.

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 and resource: fetch query-engine vitals from every query-service node, covering request rate, active/queued counts, memory, GC and uptime. It explicitly separates itself from get_cluster_metrics (node hardware) and get_cluster_health_snapshot, so an agent can route without opening other schemas.

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 an explicit trigger condition: use it after get_cluster_metrics/get_cluster_health_snapshot show healthy infra but queries are still slow. It also states hard prerequisites (self-managed Couchbase Server 7.6+, Capella rejected) and the implied exclusion of hardware-level troubleshooting.

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