list_agent_evaluations
Lists Otto and Now Assist evaluation runs for AI agents and skills, showing status, evaluation type, run type, dataset and strategy. Filter by use case, status or run type, and optionally include available eval strategies.
Instructions
List Otto / Now Assist evaluation runs (sys_one_extend_batch_run) for AI agents and skills: status, evaluation type (agentic_ai, conversational_ai), run type, dataset and strategy. Optionally list the available evaluation strategies.
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": "list_agent_evaluations"
}
}Input Schema
| Name | Required | Description | Default |
|---|---|---|---|
| limit | No | Max records (default 25) | |
| status | No | draft, in_progress, completed, error, cancelled, archived | |
| run_type | No | eval_run, test_run or auto_prompt_tuning | |
| usecase_id | No | sys_id of the agent / use case / skill under test | |
| evaluation_type | No | agentic_ai or conversational_ai | |
| include_strategies | No | Also list eval strategies (sys_one_extend_eval_strategy) |