Forecast demand series
forecast_demand_seriesUse this when someone pastes past sales numbers and asks what to expect next month, next quarter or next season. Takes 3 to 365 monthly, weekly or daily totals (oldest first) and returns the next periods with an 80 percent range, the model used (Holt-Winters seasonal, damped trend, Croston for intermittent demand, or moving average) and why. Works without a connected store.
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": {
"sales": "<sales>"
},
"name": "forecast_demand_series"
}
}Input Schema
| Name | Required | Description | Default |
|---|---|---|---|
| sales | Yes | Past sales totals per period, oldest first. | |
| period | No | Granularity of the sales list. | monthly |
| horizon | No | Periods to forecast: up to 12 monthly, 26 weekly, 90 daily. |
Output Schema
| Name | Required | Description | Default |
|---|---|---|---|
| lower | Yes | ||
| notes | Yes | ||
| trend | Yes | ||
| upper | Yes | ||
| method | Yes | ||
| period | Yes | ||
| forecast | Yes | ||
| confidence | Yes | ||
| seasonality | Yes | ||
| connect_hint | No | How to get this done automatically on live store data. | Forthcast does this automatically for Shopify stores: https://apps.shopify.com/forthcast |
| method_label | Yes | ||
| history_points | Yes | ||
| history_average | Yes |