explain_alert
Get the complete evidence chain for an alert, including the model's claim, confidence, verifier's reasoning, and cited standard, so supervisors can judge alerts independently.
Instructions
Return the full evidence chain behind one alert.
Gives the proposing model's claim, its confidence, the verifier's reasoning and the standard cited, so a supervisor can judge the alert rather than take it on trust.
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": {
"alert_id": "<alert_id>"
},
"name": "explain_alert"
}
}Input Schema
| Name | Required | Description | Default |
|---|---|---|---|
| alert_id | Yes | ||
| video_id | No |
Output Schema
| Name | Required | Description | Default |
|---|---|---|---|
No arguments | |||