Skip to main content
Glama

MONARK

gate

Coverage-gated decision from the real HIKAE L3 policy (commit/defer/abstain) over a caller-carried authorization budget B_t. Dispatches on task_class. For 'btc-dir-15m' it conformalizes against a committed synthetic calibration derived from the HIKAE S2a instrument (seed 101, n=300 draw), declared synthetic — a plumbing fixture, not a measured predictor. For 'cascade-liquidable-24h' no cascade calibration is committed; the gate abstains (under_calib) on this class. When the caller instead supplies a calibration (its own nonconformity scores plus a mode: interval ⇒ region [yhat - q̂, yhat + q̂], or set ⇒ a conformal set over caller candidates), the gate conformalizes against THOSE caller-supplied scores (BYO): 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. The gate only emits a decision; it never calls the named tool.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
paramsYes
predictionYes

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault
toolYes
allowYes
actionYes
intentYes
reasonYes
verdictYes
schema_versionYes
remaining_budgetYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A3.9/5.0
Behavior5/5

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

With no annotations, the description carries the full burden and does so richly: it discloses that MONARK does not see/store/verify caller data, does not validate supplied scores, that coverage holds only for exchangeable future points and is voided by distribution shift, and that the gate never invokes the named tool. These are exactly the behavioral traits an agent needs and cannot get from structured fields.

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

Conciseness3/5

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

The core decision is front-loaded, but the body is a dense run-on block with implementation trivia ('seed 101, n=300 draw', 'ADR-M007 D7') that inflates length without helping an agent select or invoke the tool. Several caveats earn their place; the fixture provenance details do not.

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?

For a complex nested tool with an output schema, the description covers behavior, the two calibration paths, and coverage caveats well, so return values need no explanation. Gaps are the absence of sibling routing guidance and any description of the top-level prediction/params envelope.

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

Parameters4/5

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

Top-level schema description coverage is 0% (prediction and params are undocumented objects), so the description must compensate, and it does: it explains the calibration object, the interval vs set mode semantics, and caller-supplied nonconformity scores. Nested properties are self-documented, but the top-level prediction/params meaning is only inferable from the prose.

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 opening sentence names the resource and output space precisely: a coverage-gated commit/defer/abstain decision over an authorization budget, dispatched on task_class. It is clear what the tool produces, though the dense domain jargon (HIKAE L3, S2a instrument) adds noise, and no sibling tool (attest/calibrate/cascade) is named to differentiate it.

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?

It explains when behavior differs by task_class and when a caller-supplied calibration triggers the BYO path, and it states that 'cascade-liquidable-24h' causes an abstain. But it never says when an agent should call gate rather than attest, calibrate, or cascade, leaving sibling selection to inference.

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

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.