get_system_resources
Reports host RAM and GPU VRAM plus currently loaded local Ollama models, so you can check available resources before choosing a model or context size for heavy jobs.
Instructions
Report host RAM + GPU VRAM and currently-loaded models. Only works for LOCAL ollama providers — returns {unavailable: true} for remote/openai-type providers. Use before picking a model or num_ctx for heavy jobs. Includes ollama_gpu: which GPU(s) the ollama server is pinned to (env) or observed using (runner process device fds).
Tool call template
This tool declares no required parameters. Add optional parameters from the input schema as needed.
{
"id": 1,
"jsonrpc": "2.0",
"method": "tools/call",
"params": {
"arguments": {},
"name": "get_system_resources"
}
}Input Schema
| Name | Required | Description | Default |
|---|---|---|---|
| provider | No |