List tool calls for an execution
GET /api/tool-calls
Returns all MCP tool calls made during a specific agent execution, ordered chronologically. Each tool call shows what tool was invoked, what arguments were passed, what result was returned, and how long it took. Use this for debugging agent behavior and auditing MCP server interactions.
Authorizations
Section titled “Authorizations ”Parameters
Section titled “ Parameters ”Query Parameters
Section titled “Query Parameters ”The agent execution to list tool calls for.
Responses
Section titled “ Responses ”Tool calls made during the execution.
List of tool calls made during a specific agent execution, ordered chronologically.
A record of a single MCP tool call made by an agent during execution. Tool calls show exactly what data the agent retrieved or what action it took on an external system.
object
Unique identifier for this tool call.
Example
tc1a2b3c-5678-9abc-def0-1234567890abThe agent execution this tool call belongs to.
Example
ex1a2b3c-5678-9abc-def0-1234567890abName of the MCP tool that was called.
Example
get_shipment_statusThe arguments passed to the tool. Structure varies by tool.
Example
{ "order_id": "4521"}The result returned by the tool. Structure varies by tool.
Example
{ "status": "in_transit", "carrier": "DHL", "tracking_number": "1Z999AA10123456784", "estimated_delivery": "2026-03-27"}Outcome of the tool call. ‘success’ means the tool returned a result. ‘error’ means the tool returned an error. ‘timeout’ means the tool did not respond in time.
Example
successHow long the tool call took in milliseconds.
Example
245Timestamp when the tool call was initiated.
Example
2026-03-25T11:42:06.000ZThe executionId query parameter is missing.
Standard error response returned by all endpoints on failure.
object
A human-readable error message describing what went wrong.
Example
Conversation not found