
Recording pending: Review and attach a tool. Follow the written guide below.
Before you begin
Use a signed-in dashboard session with permission to manage the workspace’s tools and edit the target agent. Have a documented action, its input schema, and any approved external integration ready.Tool management currently rejects API-key credentials in the documented implementation. Use the authenticated dashboard workflow for tool management. An endpoint in the API reference does not mean a personal API key can call it.
Review and attach
1
Open the workspace tool
Open Tools. Select an existing webhook or client tool to inspect its configuration. This procedure assumes the workspace already has an approved tool to attach.The tool detail view shows its configuration. Keep the tool identifier and confirm that it belongs to the intended workspace.
2
Define the action
Give the tool a clear name and description. Identify which inputs are required, what a successful result contains, and how errors should be handled. Keep one tool focused on one understandable action.
3
Review access and credentials
Confirm that the workspace can access the resource and that its credentials are stored through the supported integration workflow. Do not put secrets into the prompt, a tool description, or an example input.Decide which actions require user confirmation and enforce access in the service that owns the data or mutation. Prompt instructions are not an authorization boundary.If you edit a webhook or client tool, select Save, then reopen the tool to check its persisted definition. Saving that shared resource is separate from publishing an agent’s attachment list.
4
Attach the intended identifiers
Open the intended agent, select its Tools page, then choose Add tool. Search for the reviewed tool and select it. Confirm that it appears in the attached tools list. Published references use
conversation_config.agent.prompt.tool_ids.MCP references use mcp_server_ids or native_mcp_server_ids. These fields identify resources; they do not establish that a server is connected, trusted, or ready to execute.5
Review the agent version
Review the attachment list and prompt together. Save a complete server draft for durable review. For an eligible managed text-only configuration, select Publish and confirm the branch and diff in Review Changes, then read the saved version back. Voice and custom-model publication remain unavailable.
Screenshot pending: An approved sample tool attached to the agent configuration.
Keep instructions and enforcement separate
The prompt should explain when the tool is relevant and how to respond when it fails. The external service should validate inputs, check access, and enforce confirmations where required. Do not let an agent’s generated arguments decide which workspace or user is authorized. For a tool that changes data, define how to handle a repeated request or an uncertain result before runtime testing. A retry must not silently create a second action.Review checklist
Troubleshooting
If a tool is unavailable in the dashboard, confirm the active workspace and resource access. If a tool-management API request returns403, check whether it used an API key: that credential type is currently rejected for these operations. Do not bypass the restriction by putting dashboard credentials into application code.
Check current availability before planning live tool execution. The API reference exposes the current schemas; versions and drafts explains how attachments become part of a saved configuration.
Frequently asked questions
Can I manage tools with a personal API key?
Can I manage tools with a personal API key?
The documented tool-management path rejects API-key credentials. Use the supported authenticated dashboard workflow.
Does saving a tool publish its agent attachment?
Does saving a tool publish its agent attachment?
No. Saving the shared tool definition and publishing an agent attachment list are different actions. Read both resources back.