prompt_effectiveness
Returns success rate, average duration, and top failure reasons for Agent templates, helping identify prompts that perform well and those needing improvement.
Instructions
Return effectiveness statistics for Agent templates.
Aggregates activity records to compute success rate, average duration, and top failure reasons per template. Also shows how many failure alchemy lessons are associated with each template.
Use this to identify which Agent templates perform well and which need prompt improvement.
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": "prompt_effectiveness"
}
}Input Schema
| Name | Required | Description | Default |
|---|---|---|---|
| template_name | No | Optional filter (e.g. "engineering-backend-architect"). Leave empty to return stats for all templates. |
Output Schema
| Name | Required | Description | Default |
|---|---|---|---|
No arguments | |||