Start a study
create_studyOpens a study, the named set of runs every backtest belongs to: call it once per question, before run_backtest. Can set a hold-out period, once and only here, that no run tests except run_held_out_test. Only the first held-out test per account and market counts, and any earlier run on the market (in any study, at any bar size) that read its days disqualifies it: set the hold-out in your first study on a market, before any run on it.
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": {
"name": "<name>"
},
"name": "create_study"
}
}Input Schema
| Name | Required | Description | Default |
|---|---|---|---|
| name | Yes | What the study tests, in a few words. | |
| hold_out | No | The days kept back from every run but run_held_out_test; set once, here. Set it in your first study on a market, before any run on it: a held-out test on days an earlier run on the market read does not count. |
Output Schema
| Name | Required | Description | Default |
|---|---|---|---|
| next | No | ||
| reason | No | ||
| status | Yes | ||
| message | No | ||
| hold_out | No | ||
| study_id | No |