[batch]
Runs multiple tool operations sequentially in one request.
Agent workflows often need several independent facts before the next decision.
Batching reduces round trips and keeps multi-tool evidence together, which is especially valuable on large workspaces.
| Name | Type | Required | Description |
|---|---|---|---|
| operations | json | Yes | Operations to run, in order. JSON array of objects like { "tool": "get_type_info", "arguments": { ... } }. |
| stopOnError | boolean | No | When true, stops after the first failure. Default is false. |
| maxOperations | number | No | Maximum number of operations allowed. Use 0 for unlimited. Default is 25. |
| maxTotalOutputChars | number | No | Maximum total output characters before truncation. Use 0 for unlimited. Default is 200000. |
Run multiple operations
{
"jsonrpc": "2.0",
"id": 1,
"method": "tools/call",
"params": {
"name": "batch",
"arguments": {
"operations": "[\n { \"tool\": \"resolve_symbol\", \"arguments\": { \"query\": \"ISolutionManager\", \"kinds\": \"Type\" } },\n { \"tool\": \"find_references\", \"arguments\": { \"symbolKey\": \"...\", \"groupBy\": \"project\" } }\n]"
}
}
}{
"success": true,
"data": {
"operationCount": 2,
"completedCount": 2,
"failedCount": 0,
"stoppedEarly": false,
"results": [
{
"tool": "get_type_info",
"result": {
"success": true,
"data": {
"name": "SolutionManager"
},
"error": null
}
},
{
"tool": "search_symbols",
"result": {
"success": true,
"data": {
"matchCount": 3
},
"error": null
}
}
]
},
"error": null
}Returns per-operation results in order