capacity_plan
Forecast when device metrics will cross a capacity threshold by analyzing historical trends, seasonality, and change points to return breach ETAs and hours remaining.
Instructions
Composite capacity planning: reads each instance once through analyze_metric to classify its trend, detect seasonality and change points, and forecast when it crosses threshold (default 90). Summary rows carry each forecast method's breach_eta (epoch seconds) and hours_until_breach per datapoint.
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": "capacity_plan"
}
}Input Schema
| Name | Required | Description | Default |
|---|---|---|---|
| device_id | No | Device ID | |
| threshold | No | Level each forecast reaches for, in the datapoint's unit (default: 90) | |
| datasource | No | Filter to a specific datasource name | |
| hours_back | No | Hours of historical data (default: 168 = 1 week) | |
| device_name | No | Device display name (used if device_id not provided) | |
| detail_level | No | Output detail level (default: summary) | summary |
Output Schema
| Name | Required | Description | Default |
|---|---|---|---|
| portal | No | The portal the call ran against, in multi-portal mode. | |
| warnings | No | ||
| device_id | Yes | ||
| threshold | Yes | The level each forecast must reach. | |
| hours_back | Yes | Hours of history each read covers. | |
| datasources | No | Full: up to five datasources and three instances each. | |
| device_name | Yes | ||
| detail_level | Yes | ||
| forecast_summary | No | Summary: one headline row per datapoint read. |