browser_batch
Run several page actions on one tab in a row, then get a fresh snapshot back — one call instead of one per step; worth it for a single action too. Steps aim with the numbers of one snapshot.
Instructions
Run several page actions on one tab in a row, then get a fresh snapshot back — one call instead of one per step; worth it for a single action too. Steps aim with the numbers of one snapshot. For something an earlier step makes appear (a suggestion list, a menu), wait for it with browser_wait forText, then aim with find instead of emsn: {"tool": "browser_click", "args": {"find": {"text": "Bluetooth headphones"}}}. Stops at the first failure, unless the step says onFail: skip (a banner that may not show). After a step the browser says changed the page, the later steps that aim by number are not run; waits and finds still are.
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": {
"actions": "<actions>"
},
"name": "browser_batch"
}
}Input Schema
| Name | Required | Description | Default |
|---|---|---|---|
| tabId | No | Tab to act on. Defaults to the foreground tab of that window. | |
| actions | Yes | ||
| snapshot | No | The snapshot after the steps. full (default): the whole of it. changes: only the lines new or changed (+) and gone (-) since snapshotId's snapshot, with the lines they sit in; the whole of it, saying why, when there is none to compare with (another page, no snapshotId) or the changes would be longer. none: no snapshot. | |
| windowId | No | Window to act on. Defaults to the frontmost window. | |
| snapshotId | No | From the snapshot the numbers were read from; required when any step names an emsn (a step may carry its own in args instead). |