Read KV-cache utilization, prefix-cache hit rate, and preemption counts for a vLLM/Ray inference target to diagnose GPU memory pressure and scheduling issues.
[READ] KV-cache utilisation, prefix-cache hit rate, and preemption count.
Args: target: Inference target name from config; omit for the default.
| Name | Required | Description | Default |
|---|---|---|---|
| target | No |
Changes observed during successful MCP inspections.
v0.6.0Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
The readOnlyHint annotation already establishes this as a safe read, and the '[READ]' marker merely restates it. The description does add value by naming the three metrics returned, but says nothing about refresh behaviour, aggregation window, or whether a missing target errors versus falling back to default.
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?
The metric list is front-loaded in one sentence and the argument note is terse. The 'Args:' block is mildly redundant formatting for a single optional parameter but carries the non-obvious default semantics, so it earns its place.
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 read-only stats tool with no output schema, listing the three reported metrics is the key missing piece an agent needs, and it is present. Only minor gaps remain, such as units or aggregation window for the reported numbers.
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 carry the load, and it does: 'Inference target name from config; omit for the default' explains both the source of valid values and the defaulting behaviour, which the bare anyOf/null schema does not convey.
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 resource (KV-cache stats) and enumerates exactly what it reports: utilisation, prefix-cache hit rate, and preemption count. This distinguishes it from siblings like engine_request_metrics and request_metrics, though it never names those siblings explicitly.
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?
There is no when-to-use guidance, no mention of alternatives among the many metrics/health tools in the sibling list, and no prerequisites. The only usage hint is the parameter note 'omit for the default', which is about input, not tool selection.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.