Tools
Tools

Delete a tool

Delete a tool. Identify the tool by toolName (its snake_case name) or toolId. **Check if other tools' `requires` reference this tool's name first**, leaving dangling requires references will fail the publish validator.

DELETE
/workspaces/{workspace}/agents/{agent}/tools/{tool}

Authorization

bearerAuth
AuthorizationBearer <token>

A personal access token from Settings > API tokens.

In: header

Path Parameters

workspace*string

Workspace slug (GET /me lists yours).

agent*string

Agent slug within the workspace.

tool*string

Query Parameters

toolId?string

The tool's id. Optional, prefer toolName.

Length1 <= length
confirm?boolean

Must be true to perform this action. It deletes something, publishes, or changes what live callers get straight away, so confirm with the user first.

Response Body

application/json

application/problem+json

application/problem+json

application/problem+json

application/problem+json

application/problem+json

application/problem+json

application/problem+json

curl -X DELETE "https://example.com/workspaces/string/agents/string/tools/string"
{
  "property1": null,
  "property2": null
}
{
  "type": "http://example.com",
  "title": "string",
  "status": 0,
  "detail": "string",
  "code": "string",
  "errors": [
    {
      "path": "string",
      "message": "string"
    }
  ],
  "estimate": {},
  "retryAfterSeconds": 0
}
{
  "type": "http://example.com",
  "title": "string",
  "status": 0,
  "detail": "string",
  "code": "string",
  "errors": [
    {
      "path": "string",
      "message": "string"
    }
  ],
  "estimate": {},
  "retryAfterSeconds": 0
}
{
  "type": "http://example.com",
  "title": "string",
  "status": 0,
  "detail": "string",
  "code": "string",
  "errors": [
    {
      "path": "string",
      "message": "string"
    }
  ],
  "estimate": {},
  "retryAfterSeconds": 0
}
{
  "type": "http://example.com",
  "title": "string",
  "status": 0,
  "detail": "string",
  "code": "string",
  "errors": [
    {
      "path": "string",
      "message": "string"
    }
  ],
  "estimate": {},
  "retryAfterSeconds": 0
}
{
  "type": "http://example.com",
  "title": "string",
  "status": 0,
  "detail": "string",
  "code": "string",
  "errors": [
    {
      "path": "string",
      "message": "string"
    }
  ],
  "estimate": {},
  "retryAfterSeconds": 0
}
{
  "type": "http://example.com",
  "title": "string",
  "status": 0,
  "detail": "string",
  "code": "string",
  "errors": [
    {
      "path": "string",
      "message": "string"
    }
  ],
  "estimate": {},
  "retryAfterSeconds": 0
}
{
  "type": "http://example.com",
  "title": "string",
  "status": 0,
  "detail": "string",
  "code": "string",
  "errors": [
    {
      "path": "string",
      "message": "string"
    }
  ],
  "estimate": {},
  "retryAfterSeconds": 0
}

Add an HTTP tool POST

Create a new HTTP tool. This call sets the minimum (name, description, method, url; displayName optional, defaults to the name). Use `set_tool_headers` / `set_tool_params` / `set_tool_requires` afterwards to fill in the rest. URLs may include `{{variable_name}}` placeholders, declare those variables with `set_plain_variable`, or for a credential `request_secret_variable` in the app or `set_secret_variable` over the MCP.

List the agent's tools GET

Return the full current agent snapshot as JSON, the agent row (name, voice, model, settings), the current version's system prompt + greeting, the tool list (each tool's name, kind, description, and for HTTP tools its url/method/headers/params/mock), the `workflow` (pre-call and post-call functions), variables (name + kind; secret values are never returned, plain values are), and the `privacy` block (recording + AI consent-disclosure enabled flags + copy, PII scrub level/categories, retention, telemetry, call-recording, null on an enabled flag means it inherits the workspace default). In the in-app builder this snapshot is already inlined every turn so calling it is just a post-edit re-read; over MCP it is the ONLY way to read the prompt/tools/variables/privacy, so call it whenever you need to see current state or confirm an edit landed. Pass `version: 'published'` (or a version number) to read the live version while a draft is open. For a cheap re-read after an edit, pass `toolName` (one tool's entry) or `sections` (only the groups you need, prompt/tools/variables/voice/behaviour/privacy/settings/model/workflow) instead of pulling the whole ~50KB snapshot. In the `model` group, `judgeModel` names the grading model (null = the platform default).