tolerance_stack_analysis
Read-only
Walk a tolerance chain across a multi-part assembly to quantify gap variation using worst-case, RSS, or Monte Carlo methods.
Instructions
Chain-walking tolerance stack analysis on a multi-part assembly.
Needs Kiln Pro.
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": {
"chain": "<chain>"
},
"name": "tolerance_stack_analysis"
}
}Input Schema
| Name | Required | Description | Default |
|---|---|---|---|
| mode | No | "normie" | "engineer" | "auto". Default: "auto". | |
| seed | No | Monte Carlo seed for reproducibility. Default: 42. | |
| brief | No | Optional user brief (auto-detects engineer mode). | |
| chain | Yes | List of part dicts. Each part: {"name": "...", "nominal_mm": float, "tol_plus_mm": float, "tol_minus_mm": float, "axis": "xy"|"z", "direction": +1|-1, "distribution": "normal"|"shifted_normal"|"uniform"}. | |
| method | No | "worst_case" (default; arithmetic sum, safest for safety-relevant gaps), "naive_rss", "bender_rss", "scholz_mean_shift", or "monte_carlo" (uses ``seed``, ``n_samples``, ``fdm_aware``). Default: "worst_case". | |
| material | No | Material id (only consulted when ``printer_id`` is set; together they look up calibration). | |
| fdm_aware | No | When method="monte_carlo", treat a printed part's height (Z) as less certain than its X/Y, as measured prints show. How much less follows the printer's calibration tier when printer_id is set. Default: true. | |
| n_samples | No | Monte Carlo sample count. Default: 10000. | |
| printer_id | No | Printer identifier (e.g. "bambu_a1") to look up calibration for. When supplied alongside ``material``, the result's confidence_warning notes the calibration tier — HIGH tightens the implied bound, LOW/UNKNOWN points the user at the slicer's flow-rate wizard. |