AgentMart Evidence Calibration
calibrateBenchmark web-extraction vendors and collect fresh reliability, quality, latency, and cost evidence across a curated URL task set. Use only after the user explicitly approves a bounded calibration batch. Calls selected external providers directly and caps each invocation at 30 provider calls.
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": {
"confirmExternalCalls": "<confirmExternalCalls>"
},
"name": "calibrate"
}
}Input Schema
| Name | Required | Description | Default |
|---|---|---|---|
| repeats | No | ||
| taskIds | No | Optional standard calibration task IDs. Leave empty to use the curated 10-task set. | |
| maxCalls | No | ||
| providerIds | No | Providers to test directly. Leave empty to test every connected provider. | |
| confirmExternalCalls | Yes | Must be true only after the user explicitly approves the provider calls and usage. |