MONARK

calibrate

split-conformal quantile at miscoverage α over caller-supplied nonconformity scores. MONARK does not see, store, or verify the caller's data or model, and does not validate that the supplied numbers are nonconformity scores of any model. Marginal 1−α coverage holds ONLY for future points exchangeable with the supplied scores; non-exchangeable data (e.g. distribution-shifted or time-ordered) voids it. Never a probability of being right.

Input Schema

TableJSON Schema

Name	Required	Description
`nMin`	Yes	Minimum calibration count (>= 1); n < nMin fails closed to under_calib.
`alpha`	Yes	Target miscoverage in the open interval (0,1).
`scores`	Yes	Caller-supplied nonconformity scores (BYO: the caller owns the score function; MONARK stays agnostic).

Output Schema

TableJSON Schema

Name	Required	Description
`n`	Yes	The number of supplied scores (echoed).
`qhat`	Yes	The conformal quantile q̂, or null when the calibration is insufficient (fail-closed).
`alpha`	Yes	The target miscoverage (echoed).
`label`	Yes	Honesty label (K-1): the marginal coverage holds only under exchangeability with the supplied scores.
`method`	Yes	The conformal method — always split.
`reason`	Yes	under_calib when q̂ is null, else null on success.
`scores_sha256`	Yes	scoresSha256(scores) in the caller's order: the audit tie to verdict.scores_sha256 (C2).

Schema Changelog

Changes observed during successful MCP inspections.

Changed3 schema fields changedOct 6, 2026

addedOutput schema / properties / scores_sha256

Added value: +{
+  "description": "scoresSha256(scores) in the caller's order: the audit tie to verdict.scores_sha256 (C2).",
+  "pattern": "^[0-9a-f]{64}$",
+  "type": "string"
+}

removedOutput schema / properties / set_digest

Removed value: -{
-  "description": "calibDigest(scores): recalculable by reference; the audit tie to verdict.calib_digest (C2).",
-  "pattern": "^[0-9a-f]{64}$",
-  "type": "string"
-}

changedOutput schema / required

Previous value: -[
-  "qhat",
-  "n",
-  "alpha",
-  "method",
-  "set_digest",
-  "label",
-  "reason"
-]New value: +[
+  "qhat",
+  "n",
+  "alpha",
+  "method",
+  "scores_sha256",
+  "label",
+  "reason"
+]

First observedSep 18, 2026

TDQS

A3.7/5.0

Behavior4/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations, the description carries the full burden, and it discloses non-obvious traits: MONARK never sees/stores/verifies the caller's data, does not validate inputs as true nonconformity scores, and the coverage guarantee is conditional on exchangeability. It stops short of describing failure behavior or performance, but the fail-closed nMin path is covered in the schema.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Four dense sentences, front-loaded with the operation before the caveats, and every clause carries real information for a statistically sensitive tool. It is compact for the amount of qualification it conveys, though the sentence density is high.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

An output schema exists, so return values need not be explained, and the description covers the trust model, the statistical guarantee, and its limits. Remaining gaps (exact response shape, failure surface) are largely delegated to the schema, but for a tool with zero annotations the operational side could be stated more explicitly.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, so alpha, nMin, and scores are already documented with units, bounds, and fail-closed behavior. The description adds framing ('BYO', MONARK agnostic) but no new per-parameter syntax or constraints, matching the baseline 3.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description names a precise operation ('split-conformal quantile at miscoverage α over caller-supplied nonconformity scores'), so an agent immediately knows this is a calibration/quantile computation rather than an attestation or gating step. It does not explicitly differentiate itself from the siblings (attest, cascade, gate), so it lands just short of a 5.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines3/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

There is no explicit when-to-use/when-not or routing to alternatives; usage must be inferred from the statistical framing. The exchangeability caveat ('holds ONLY for future points exchangeable...') is a validity condition rather than invocation guidance, but it does tell the agent when the result is meaningful.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

All MONARK tools Inspect

Try in Browser

One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.