record_interaction
Log tool-call results to measure AI agent reliability. Track success, latency, and errors after every important call.
Instructions
Log one tool-call result. Call this after every important tool use so reliability can be measured.
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": {
"agent_id": "<agent_id>",
"tool_name": "<tool_name>",
"success": "<success>"
},
"name": "record_interaction"
}
}Input Schema
| Name | Required | Description | Default |
|---|---|---|---|
| success | Yes | ||
| agent_id | Yes | ||
| metadata | No | ||
| tool_name | Yes | ||
| latency_ms | No | ||
| session_id | No | ||
| error_message | No |