Retrieve each GPU adapter's usage, engines, dedicated and shared memory, temperature, and top processes to monitor graphics hardware and identify heavy consumers.
GPUs: each adapter's usage, engines (3D, copy, video...), dedicated and shared memory, temperature, and the processes using the GPU most.
| Name | Required | Description | Default |
|---|---|---|---|
No arguments | |||
Changes observed during successful MCP inspections.
v0.1.0Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
The annotations already declare readOnlyHint=true, idempotentHint=true, destructiveHint=false, and closed-world, so the safety profile is fully covered. The description adds the useful behavioral detail that results are per-adapter and include the top processes per GPU, but says nothing about behavior when no GPU exists, error cases, or cost of the call.
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?
One compact sentence that front-loads the resource and then lists the payload fields in a scannable order. Nothing is padded, though the fragmentary style (no verb, trailing '...') reads more like a field label than a tool contract.
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?
With no input parameters and no output schema, the description's main job is to convey what comes back, and it does so field by field (usage, engines, memory types, temperature, consuming processes). Only the edge cases — multi-GPU ordering, behavior on machines without GPUs — are unaddressed.
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 takes zero parameters, so there is nothing for the description to compensate for and the baseline of 4 applies. The description correctly implies a full, unfiltered snapshot rather than a filtered query.
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 identifies the resource (GPUs) and enumerates the data fields returned — per-adapter usage, engines, dedicated/shared memory, temperature, top processes — so a reader knows what they'd get. But it is a noun-phrase fragment with no verb, and it does not distinguish this tool from siblings like get_hardware or get_system_overview, which plausibly overlap.
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 at all: no condition that selects this over get_hardware, get_system_overview, or get_sensors. The agent must infer that this is the GPU-specific view purely from the name and field list.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.