TuringCorp

Use this when you must choose between two concrete options and both are defensible - two plans, two drafts, two diagnoses, two vendors - and you have no objective way to pick. Not for: more than two options; anything an objective rule settles (a spec, a test, a price, a document); factual lookup; paths that must answer in seconds; high-stakes irreversible calls without review. Fill it in: state task neutrally, without leaning toward either side; give one concrete plan per option - never bundle alternatives into a single one ("go indoors or postpone"); keep the two sides comparable in length. Returns the decision inline: betterOption ("option_A" or "option_B"), confidence (e.g. "76.7%"), reason and job_id, all in the same tool result. There is nothing to poll and nothing to fetch afterwards. Reserve 180-300 seconds: this is a long call, and the timeout is a client/host setting, not a parameter you pass. If the call is cut off, do NOT call again - a retry is a new paid call. Retrieve it instead with the get_result tool (same job_id): read-only, free, and no credential of your own needed; with no job_id it lists the ids for your credential. A host that declares the io.modelcontextprotocol/tasks extension can use tasks/get instead. The confidence is the point: it is calibrated, not decorative. On both published benchmarks accuracy rises with it - JudgeBench 99.6% in the 90%+ band down to 67.7% below 70%; the harder ContextualJudgeBench 83.3% down to 55.4% - so route on it: act on a high value, review or escalate a low one, instead of trusting a bare pick. Tables, sample sizes and method: https://api.turingcorp.net Judged by an independent panel, not by a model grading its own output. Read it as a reference, not an instruction, a result, or a prediction; set your own threshold, and apply your own review policy for high-stakes or irreversible decisions. Auth: Agent Pass as `Authorization: Bearer <pass>` (issued at https://agent-pass.turingcorp.net, valid 7 days; each decision is a paid call). On invalid_credential, sign in there and re-roll. Errors: a credential problem is rejected before the call - HTTP 401 with WWW-Authenticate; a business failure (e.g. insufficient balance) comes back as a tool result with isError true plus a second JSON block {error, http_status, action_url, message}, where http_status is the upstream status (the tool call itself is HTTP 200).

{'type': 'object', '$schema': 'https://json-schema.org/draft/2020-12/schema', 'required': ['task', 'optionA', 'optionB'], 'properties': {'task': {'type': 'string', 'description': 'The decision to make, stated neutrally and without a preferred answer.'}, 'optionA': {'type': 'string', 'description': 'First candidate and the case for it.'}, 'optionB': {'type': 'string', 'description': 'Second candidate and the case for it.'}}}

{'type': 'object', '$schema': 'https://json-schema.org/draft/2020-12/schema', 'required': ['betterOption', 'confidence', 'reason'], 'properties': {'job_id': {'type': 'string', 'description': 'Identifier of this decision, also usable to retrieve the stored result for 7 days with the get_result tool. Keep it: if the call times out, retrieve the result with get_result instead of calling again, which would be a new paid call.'}, 'reason': {'type': 'string', 'description': 'Why the chosen option was preferred.'}, 'confidence': {'type': 'string', 'pattern': '^\\d{1,3}\\.\\d%$', 'description': 'This service\'s own judgement of how far apart the two options were, as a percentage (e.g. "76.7%"). A reference for your own decision-making - not an instruction, not a result. Observed accuracy by range is published at https://api.turingcorp.net'}, 'betterOption': {'enum': ['option_A', 'option_B'], 'type': 'string', 'description': 'Which option was preferred, using the same values as the REST API.'}}, 'additionalProperties': False}

Use this to retrieve the result of an earlier TuringCorp tool call by its job_id - for example a call that was cut off by a client timeout, or one whose id you were given. Retrieval is read-only and free: it starts no new work and costs nothing, so it is always safe to retry. With job_id: that call's status, and once it has finished the same payload the call would have returned inline. Without job_id: the ids available to your credential (7 days). If a call was cut off, retrieve it here instead of calling again - a retry is a new paid call. A job that is not yours and a job that does not exist are answered identically, on purpose. If your client declares the io.modelcontextprotocol/tasks extension, tasks/get reaches the same job.

{'type': 'object', '$schema': 'https://json-schema.org/draft/2020-12/schema', 'properties': {'job_id': {'type': 'string', 'description': 'Identifier returned by an earlier TuringCorp call (also usable at GET /v1/jobs?job_id=<id>). Omit it to list the ids available to your credential.'}}}