Update Eval Rubric
updateEvalRubricEdit a single Agent-specific evaluation rubric's title and/or description. The edit produces a NEW rubric (with a new id and slug) so previously scored Runs stay attributed to the original criterion; the response contains the new rubric.
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": {
"agentId": "<agentId>",
"rubricId": "<rubricId>"
},
"name": "updateEvalRubric"
}
}Input Schema
| Name | Required | Description | Default |
|---|---|---|---|
| title | No | Short, human-readable Pass/Fail rubric title. | |
| agentId | Yes | The agent's unique identifier (Assignment ID) | |
| rubricId | Yes | The custom rubric's unique identifier | |
| description | No | A 1-2 sentence Pass condition phrased as a question. | |
| selected_automation_revision_id | No | The automation revision this edit is being made at. Pass a draft and the edit is folded into that draft itself; pass the active revision and the edit lands on a draft branched from it. A historic revision is rejected — it cannot be activated from without an explicit rebase. A revision belonging to a different automation is ignored, and the edit targets the automation the addressed agent belongs to. Omit to target the automation's active revision. |