API ReferenceAgents

Get a tool

GET
/{appUid}/agent/tools/{name}

Authorization

bearerAuth
AuthorizationBearer <token>

Authorization for API

In: header

Path Parameters

name*string
appUid*string

Your app's unique id. Find it in the console under the app's Settings, or in the URL of any app page.

Formatuuid

Query Parameters

mode?string

Projection mode for the tool descriptors. Omit for the default projection.

Response Body

application/json

application/json

application/json

curl -X GET "https://example.com/497f6eca-6276-4993-bfeb-53cbbbba6f08/agent/tools/string"
{  "ok": true,  "tool": {}}

List tools

The key's toolbox — the same set the agent itself sees, derived from the policies bound to its role. Nothing here is configured as a tool list: it is what the agent is *permitted* to do, projected into tool descriptors. Equivalent to MCP `tools/list`.

Call a tool

Runs exactly this tool, with no model in the loop — deterministic, and cheaper than an orchestrated run when you already know what you want done. The body is the tool's arguments. It accepts `{ "input": { … } }`, `{ "arguments": { … } }`, or the bare argument object. **Governance still applies.** A tool your policy marks high-risk does not execute here either: the response is `202` with a `runUid`, the call waits in the approval inbox, and you poll the run for its outcome. The direct door is faster, not looser. Equivalent to MCP `tools/call`.