---
title: "Execute evaluated tool"
method: POST
path: "/ai/evaluatedTools/execute"
tags: ["AI - Evaluated Tools"]
---

# Execute evaluated tool

`POST /ai/evaluatedTools/execute`

Execute an evaluated tool from inside the sandbox

## Request body

- object — Body schema for the evaluated-tool execute endpoint. Identity (workspace, message) is derived from the bearer token and never trusted from the body.
  - `id` string, required — Id of the evaluated tool to execute (the same id the model sees in its tool surface, e.g. `tools_send_email`).
  - `input` unknown

## Response `200`

Successful response

- object
  - `data` unknown
  - `batchUuid` string
  - `runUuid` string
  - `creditsUsedCount` number

## Other responses

- `400` — Bad request
- `401` — Unauthorized
- `404` — Not found
- `500` — Internal server error

---

[API](https://skmtc.net/getcargo/apis/cargo-api.md) · [All operations](https://skmtc.net/getcargo/apis/cargo-api/llms.txt) · [OpenAPI document](https://skmtc-service-staging.skmtc.workers.dev/v1/apis/getcargo/cargo-api/versions/1d5a19e01d83/schema)