vm_health_rca

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

Annotations only declare readOnlyHint=true, so the description carries the behavioral burden and does so well: it discloses the ranking logic, that events are correlated one-finding-per-VM-and-code, and the superseding rule (VM started after the event, or engine reported back up and it is up now). It also notes eventsOutsideWindow behavior.

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 the key claim ('VM problems ranked worst first, in one call') and every subsequent sentence carries information. It is dense and long, but the length is justified by the correlation rules; a small trim of the severity rubric would not hurt.

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 and this is a complex diagnostic tool, yet the description explains the finding model, ranking, event correlation, and every argument. An agent has enough to invoke it and interpret results without opening anything else.

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 0%, so the description must compensate, and it does: events_limit (1-1000, default 200), events_window_hours (1-720, default 24, and how out-of-window events are surfaced), and target (engine target name from config, omittable for default). All three parameters are fully documented.

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 — VM problems ranked worst first, in one call — with an explicit read-only marker. It implicitly distinguishes itself from the sibling *rca tools (host_health_rca, engine_health_rca, storage_capacity_rca) by scoping to VMs.

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 a concrete severity rubric (high/medium/info/low) tied to VM states, and explicitly routes to an alternative: 'check storage_capacity_rca' for storage I/O errors. It also flags a false-positive case — 'Down VMs without HA are normal' — which is genuine when-not-to-alarm guidance.

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