Skip to main content
A client tool describes an action intended for the application hosting the conversation, such as opening a help panel. The stored definition describes the action; your application’s handler would perform it through a supported runtime integration.
Dashboard tool management is available. Personal API keys are rejected for tool-management operations. Saving a client tool does not install a handler or establish live client-tool execution.

​
Create and inspect the definition

Use a signed-in dashboard session with permission to manage workspace tools and edit the intended agent.
1

Open the client-tool form

Open Tools and select Add client tool. Choose a name that describes one action, such as open_help_panel.
2

Describe inputs and results

Explain when the tool is appropriate and what each parameter means. Use the parameter schema to describe required values. Keep credentials and privileged server operations out of a client-side action.
3

Review the response policy

Review expects_response, response_timeout_secs, and the execution settings. Decide whether your planned handler needs to return information or only update the interface.
4

Save and attach separately

Select Add tool, then reopen the resource and inspect its stored definition. Follow tool attachment to add its ID to the agent. Save an agent draft and read the attachment back; tool creation and agent publication are different actions.

​
Definition fields

Before runtime integration, prepare examples for an unknown action, invalid arguments, a handler failure, and a repeated request. Use client events as contract guidance, not proof of an available first-party SDK.

​
Frequently asked questions

No. It stores a definition. This form does not upload application code or create a hosted execution environment.
No. Client arguments are not credential storage. Keep privileged credentials on your server and enforce access there.