Skip to main content
Glama

OneQAZ Trading Intelligence

by io.github.wnsod
OverviewDiscussionsAdmin

Signal Calibration

get_signal_calibration
Read-onlyIdempotent

Purpose: Reliability diagram data for Level-1 signal confidence — realized hit rate per confidence bucket ([0.5,0.6) ... [0.9,1.0]) with ECE summary. Lets an agent verify whether a 0.9-confidence signal actually hits ~90%. Triggers (casual questions too): "is your confidence calibrated?", "confidence 0.9 믿어도 돼?", "시그널 확신도 실제 적중률 보여줘", "how reliable are signal confidences?". When to call: before trusting get_signals confidence values as probabilities. Prerequisites: none. Next steps: get_prediction_accuracy (macro-layer skill), get_signals. Caveats: snapshot is daily (per-market day; markets[].stale flags a lagging market); read the observation window from markets[].observation_window_utc; every interval is judged 30 minutes after the signal (meta.judgment_horizon); n is nominal (correlated trials — see meta.sample_caveat); read intervals[*].quality.status before citing a cell (withheld / degenerate / non_monotone) and cite all_intervals_excluding_withheld, not all_intervals.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
variantNo"v1" (raw heuristic confidence, default) or "v2" (outcome-based shadow confidence — RCA C2, accumulating since 2026-07-21)v1
intervalNoOptional candle interval filter (e.g. 15m, 30m, 240m, 1d)
market_idNoOptional filter (crypto | kr_stock | us_stock)

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault
full_dataNo
timestampYesRFC3339 UTC, server build time
disclaimerYesCanonical compliance disclaimer (always present)
request_idYes32-hex per-response correlation id
is_real_moneyNo
data_classificationNo
is_investment_adviceNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changed
    • addedInput schema / additionalProperties
      Added value: +false
  2. Changed2 schema fields changed
    • addedOutput schema / properties
      Added value: +{
+  "data_classification": {
+    "anyOf": [
+      {
+        "const": "research_information_only",
+        "type": "string"
+      },
+      {
+        "type": "null"
+      }
+    ],
+    "default": null
+  },
+  "disclaimer": {
+    "description": "Canonical compliance disclaimer (always present)",
+    "type": "string"
+  },
+  "full_data": {
+    "anyOf": [
+      {
+        "additionalProperties": true,
+        "description": "`full_data` for get_signal_calibration — 실응답에서 추출(2026-09-23).",
+        "properties": {
+          "markets": {
+            "additionalProperties": true,
+            "type": "object"
+          },
+          "meta": {
+            "additionalProperties": true,
+            "type": "object"
+          },
+          "snapshot_day": {
+            "anyOf": [
+              {
+                "type": "string"
+              },
+              {
+                "type": "null"
+              }
+            ],
+            "default": null
+          },
+          "variant": {
+            "anyOf": [
+              {
+                "type": "string"
+              },
+              {
+                "type": "null"
+              }
+            ],
+            "default": null
+          }
+        },
+        "type": "object"
+      },
+      {
+        "type": "null"
+      }
+    ],
+    "default": null
+  },
+  "is_investment_advice": {
+    "anyOf": [
+      {
+        "const": false,
+        "type": "boolean"
+      },
+      {
+        "type": "null"
+      }
+    ],
+    "default": null
+  },
+  "is_real_money": {
+    "anyOf": [
+      {
+        "const": false,
+        "type": "boolean"
+      },
+      {
+        "type": "null"
+      }
+    ],
+    "default": null
+  },
+  "request_id": {
+    "description": "32-hex per-response correlation id",
+    "type": "string"
+  },
+  "timestamp": {
+    "description": "RFC3339 UTC, server build time",
+    "type": "string"
+  }
+}
    • addedOutput schema / required
      Added value: +[
+  "disclaimer",
+  "request_id",
+  "timestamp"
+]
  3. Changed7 schema fields changed
    • addedInput schema / properties / interval / anyOf
      Added value: +[
+  {
+    "type": "string"
+  },
+  {
+    "type": "null"
+  }
+]
    • addedInput schema / properties / interval / description
      Added value: +"Optional candle interval filter (e.g. 15m, 30m, 240m, 1d)"
    • removedInput schema / properties / interval / type
      Removed value: -"string"
    • addedInput schema / properties / market_id / anyOf
      Added value: +[
+  {
+    "type": "string"
+  },
+  {
+    "type": "null"
+  }
+]
    • addedInput schema / properties / market_id / description
      Added value: +"Optional filter (crypto | kr_stock | us_stock)"
    • removedInput schema / properties / market_id / type
      Removed value: -"string"
    • addedInput schema / properties / variant / description
      Added value: +"\"v1\" (raw heuristic confidence, default) or \"v2\" (outcome-based shadow confidence — RCA C2, accumulating since 2026-07-21)"
  4. Changed1 schema field changed
    • addedInput schema / properties / variant
      Added value: +{
+  "default": "v1",
+  "type": "string"
+}
  5. Added

TDQS

A4.6/5.0
Behavior5/5

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

Annotations only cover readOnly/idempotent/openWorld; the description adds substantial behavior the agent could not otherwise know: daily per-market snapshot with stale flags, the observation-window field, a 30-minute judgment horizon, nominal n with correlated-trial caveat, and quality.status values (withheld/degenerate/non_monotone) that gate whether a cell may be cited.

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?

Front-loads purpose, then uses labeled sections (Triggers, When to call, Prerequisites, Next steps, Caveats) so an agent can scan to the relevant part. The Caveats block is a dense run-on, but each clause carries operational weight rather than filler.

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

Completeness5/5

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

An output schema exists, so return-value explanation is unnecessary; the description instead supplies the interpretive context the schema cannot (which field to cite, which quality statuses disqualify a cell). Nothing needed to call or correctly interpret the tool is missing.

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 description coverage is 100% and the variant/interval/market_id semantics (including v1 vs v2 and accumulation date) are already documented in the schema. The description adds no parameter-level syntax or default guidance beyond what structured fields provide, so the baseline 3 applies.

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

Purpose5/5

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

States a specific resource (reliability diagram data for Level-1 signal confidence), the exact output shape (realized hit rate per confidence bucket with ECE summary), and the agent-facing question it answers ('verify whether a 0.9-confidence signal actually hits ~90%'). This clearly separates it from siblings like get_signals (raw values) and get_structure_calibration (a different layer).

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

Usage Guidelines5/5

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

Explicit 'When to call: before trusting get_signals confidence values as probabilities,' plus 'Prerequisites: none' and 'Next steps: get_prediction_accuracy, get_signals.' Casual-language triggers are also enumerated, removing inference from the routing decision.

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

All OneQAZ Trading Intelligence toolsInspect
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.

Resources