summarize-experiment
Retrieve experiment overview, topN runs sorted by metric or start time, and metric statistics (min, max, mean) in a single call.
Instructions
Aggregated experiment view: experiment overview + topN runs (sorted by metric or start_time) + metric stats (min/max/mean across topN) in a single call. Replaces 3-5 round-trips of get-experiment + search-runs + get-best-run.
Tool call template
Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.
{
"id": 1,
"jsonrpc": "2.0",
"method": "tools/call",
"params": {
"arguments": {
"experimentId": "<experimentId>"
},
"name": "summarize-experiment"
}
}Input Schema
| Name | Required | Description | Default |
|---|---|---|---|
| experimentId | Yes | Experiment ID | |
| topN | No | Number of top runs to return (default 5, max 20) | |
| metric | No | Metric key to sort topN by; if omitted, sorts by start_time DESC | |
| ascending | No | 'true' or 'false' (default 'false'). Only meaningful when metric is set. | |
| extractFields | No | Comma-separated dotted paths to project from response. Use `*` as wildcard. |