---
title: "PUT /simulate/api/harness-environments/{id}/evaluations/tool-call/"
method: PUT
path: "/simulate/api/harness-environments/{id}/evaluations/tool-call/"
tags: ["simulate"]
---

# PUT /simulate/api/harness-environments/{id}/evaluations/tool-call/

`PUT /simulate/api/harness-environments/{id}/evaluations/tool-call/`

## Request

- Base URL: `http://localhost:8000`
- URL: `http://localhost:8000/simulate/api/harness-environments/{id}/evaluations/tool-call/`
- Auth: one of:
  - API key in header `X-Api-Key`
  - API key in header `X-Secret-Key`

Turn the tool-call judge on or off for this environment. Returns the full environment detail. Turning it on is refused for a hosted voice environment with no agent version yet.

## Request body

- HarnessEnvironmentToolCallEvaluation
  - `enable_tool_evaluation` boolean, required

## Response `200`

OK

- HarnessEnvironmentDetail
  - `id` string, uuid, required
  - `overview` HarnessEnvironmentOverview, required
    - `id` string, uuid, required
    - `name` string, required
    - `description` string, nullable, required
    - `domain` string, nullable, required
    - `source_kind` string, required
    - `agent_type` 'voice' | 'chat', required
    - `status` 'building' | 'running' | 'completed' | 'failed', required
    - `stage` string, required
    - `scenario_count` integer, required
    - `sub_goals_count` integer, nullable, required
    - `tools_count` integer, nullable, required
    - `runs_count` integer, required
    - `last_updated` string, date-time, nullable, required
    - `created_at` string, date-time, required
    - `flows_count` integer, nullable, required
    - `guardrails_count` integer, nullable, required
    - `personas_count` integer, nullable, required
    - `evaluations_count` integer, required
    - `run` HarnessEnvironmentRunLink, required
      - `run_test_id` string, uuid, nullable, required
      - `test_execution_id` string, uuid, nullable, required
      - `simulation_url` string, nullable, required
    - `agent` HarnessEnvironmentAgent, nullable, required
      - `id` string, uuid, required
      - `name` string, nullable, required
      - `provider` string, nullable, required
      - `versions_count` integer, required
      - `active_version` string, nullable, required
  - `contract` HarnessEnvironmentContract, nullable, required
    - `agent` string, nullable
    - `one_liner` string, nullable
    - `modality` string, nullable
    - `call_direction` string, nullable
    - `system_prompt_excerpt` string, nullable
    - `tools` object[], nullable
    - `real_use_cases` string[], nullable
    - `hard_constraints` string[], nullable
    - `runtime` object, nullable
    - `dependencies` object[], nullable
    - `runtime_dependencies` object[], nullable
    - `implementation` string, nullable
    - `tool_entrypoints` object[], nullable
    - `data_store` object, nullable
    - `open_questions` string[], nullable
    - `amendments` HarnessEnvironmentAmendment[], required
      - `subject` string, required
      - `note` string, required
    - `sub_goals` HarnessEnvironmentCatalogueSubGoal[], required
      - `name` string, required
      - `what` string, required
      - `kind` 'checkpoint' | 'judge', required
      - `claim` string, required
      - `check` string, required
    - `end_conditions` HarnessEnvironmentEndConditions, required
      - `max_turns` integer, nullable, required
      - `max_duration_seconds` integer, nullable, required
      - `clock` 'real-time' | 'stepped', required
      - `ended_reasons` string[], required
    - `notes` string, nullable
    - `chosen_evals` string[], nullable
    - `provenance` HarnessEnvironmentProvenance, required
      - `source` object, required
      - `built_by` 'alk' | 'repository', nullable, required
      - `attempt` integer, nullable, required
      - `snapshot` string, nullable, required
      - `digests` object, required
      - `authored_at` object, required
  - `world` HarnessEnvironmentWorld, nullable, required
    - `runtime` object, required
    - `personas` HarnessEnvironmentPersona[], required
      - `name` string, nullable
      - `scenario_keys` string[], required
    - `stores` HarnessEnvironmentStore[], required
      - `capability` string, required
      - `engine` string, required
      - `strategy` string, required
      - `tables` HarnessEnvironmentStoreTable[], required
        - `name` string, required
        - `rows` integer, required
      - `total_rows` integer, required
  - `scenarios` HarnessEnvironmentScenario[], required
    - `scenario_key` string, required
    - `scenario_id` string, uuid, required
    - `name` string, required
    - `instruction` string, required
    - `use_case` string, nullable, required
    - `branch` string, nullable, required
    - `tests` string, nullable, required
    - `fixture` object, nullable, required
    - `steps` integer, nullable, required
    - `sub_goals` HarnessEnvironmentSubGoal[], required
      - `name` string, required
      - `what` string
      - `kind` 'checkpoint' | 'judge'
      - `claim` string
    - `persona` object, nullable, required
    - `situation` string, nullable, required
    - `outcome` string, nullable, required
    - `status` string, required
    - `call_execution_id` string, uuid, nullable, required
  - `evaluations` HarnessEnvironmentEvaluations, required
    - `selected` HarnessEnvironmentSelectedEval[], required
      - `name` string, required
      - `description` string, required
      - `source` 'system' | 'custom', required
      - `tags` string[], required
      - `required_keys` string[], required
      - `agent_type` 'voice' | 'chat', required
      - `modality` 'voice' | 'text' | 'any', required
      - `credits_per_run` number, required
      - `charges_judge_tokens` boolean, required
      - `inputs` HarnessEnvironmentEvalInput[], required
        - `key` string, required
        - `source` string, required
        - `label` string, required
      - `id` string, uuid, required
      - `runnable` boolean, required
      - `editable` boolean, required
    - `results` HarnessEnvironmentResult[], required
      - `scenario_key` string, required
      - `status` string, required
      - `attempt_number` integer, required
      - `evaluations` object[], required
      - `coverage` object, required
  - `settings` HarnessEnvironmentSettings, required
    - `schema_version` string, nullable, required
    - `source` object, required
    - `agent` HarnessEnvironmentAgentSettings, required
      - `connector` string, nullable, required
      - `mode` string, nullable, required
      - `call_direction` string, nullable, required
      - `config` object, required
      - `secret_refs` string[], required
      - `secrets` string[], required
      - `credential_files` HarnessEnvironmentCredentialFile[], required
        - `environment_name` string, required
    - `runtime` object, nullable, required
    - `security` object, nullable, required
    - `artifacts` object, nullable, required
    - `scenario_count` integer, nullable, required
    - `seed` integer, nullable, required
    - `enable_tool_evaluation` boolean, required

## Other responses

- `default`: Default error response

---

[API](https://skmtc.dev/futureagi/apis/future-agi-management-api.md) · [All operations](https://skmtc.dev/futureagi/apis/future-agi-management-api/llms.txt) · [OpenAPI document](https://skmtc.dev/futureagi/apis/future-agi-management-api/revisions/c8684118e142?raw)