Next Unraid systemMetricsCpu event

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

The description adds meaningful behavioral context beyond the annotations: it blocks until an event arrives, the subscription is fixed/pre-configured, the payload is bounded, and the connection self-terminates after one delivery. This is genuinely useful for an agent deciding whether to call a potentially blocking tool. No contradiction with readOnlyHint/idempotentHint; one minor gap is the lack of any timeout mention.

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?

A single 16-word sentence where every element earns its place: mechanism ('wait'), scope ('this fixed GraphQL subscription'), output contract ('one bounded payload'), and lifetime ('then disconnect'). Well-structured and front-loaded with the core waiting behavior.

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 zero-parameter, one-shot subscription with strong safety annotations, the description covers the essential contract: what happens, what is returned, and that it terminates. Since there is no output schema, a slightly richer indication of payload contents would help, but the resource name (CPU metrics) and the bounded-payload statement provide adequate grounding for an agent.

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 has zero parameters and the schema covers 100% of them, so the baseline is 4. There is nothing for the description to add about parameter semantics, and it correctly attempts nothing. The 'one bounded payload' phrasing addresses output rather than inputs, which is appropriate here.

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 states a specific behavior ('Wait for the next event... return one bounded payload, then disconnect') tied to a named resource (systemMetricsCpu in the name/title). It is clear what the tool does, and the one-shot disconnect semantics differentiate it from a continuous streaming subscription. However, the description is generic across all 'next_*' subscription siblings; resource differentiation relies on the name rather than the description itself.

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?

No explicit when-to-use or when-not-to-use guidance is provided. The waiting/push semantics only loosely imply an event-driven use case versus polling query_metrics. With near-twin siblings like unraid_v4371_next_system_metrics_cpu_telemetry, the agent receives no help distinguishing which subscription to select.

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