Request for the client or the agent to execute the specified tool.
| JSON representation |
|---|
{
"id": string,
"displayName": string,
"args": {
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 unique identifier of the tool call. If populated, the client should return the execution result with the matching ID in |
displayName |
Output only. Display name of the tool. |
args |
Optional. The input parameters and values for the tool in JSON object format. |
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 to execute. 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 to execute. |
| End of mutually exclusive fields. | |