The execution result of a specific tool from the client or the agent.
| JSON representation |
|---|
{
"id": string,
"displayName": string,
"response": {
object
},
"parentToolCallId": string,
"agentName": string,
// The following is a list of mutually exclusive fields. At most one of the
// fields will be set in a response:
"tool": string,
"toolsetTool": {
object ( |
| Fields | |
|---|---|
id |
Optional. The matching ID of the |
displayName |
Output only. Display name of the tool. |
response |
Required. The tool execution result in JSON object format. Use "output" key to specify tool response and "error" key to specify error details (if any). If "output" and "error" keys are not specified, then whole "response" is treated as tool execution result. |
parentToolCallId |
Output only. The id of the tool call that caused this one, when it was issued by a sub-agent working on behalf of a parent call. Empty for top-level calls. Lets a client group a sub-agent's work under the call that started it instead of rendering every step as a sibling. |
agentName |
Output only. Human-readable name of the agent that issued this call, e.g. "Contract Architect". Empty when the root agent issued it. |
| The identifier of the tool that got executed. It could be either a persisted tool or a tool from a toolset. The following is a list of mutually exclusive fields. At most one of the fields will be set in a response: | |
tool |
Optional. The name of the tool to execute. Format: |
toolsetTool |
Optional. The toolset tool that got executed. |
| End of mutually exclusive fields. | |