Skip to main content
Glama
Sign In

OneQAZ Trading Intelligence

by io.github.wnsod
OverviewDiscussionsAdmin

Prediction Accuracy

get_prediction_accuracy
Read-onlyIdempotent

Call this first when judging how OneQAZ's macro calls have held up — per-cell hit rates with honest baselines; granularity="monthly" for the month-by-month trend. Purpose: Per-cell (category, target_market, lag_bucket) hit rates WITH the honest baselines (schema 1.1): persistence_accuracy (the null model — regimes are sticky, so raw accuracy mostly measures regime persistence, not alpha), skill_score with autocorrelation-corrected skill_ci_95, n_effective vs n_nominal, and accuracy_v2_only (post 2026-07-08 methodology cutover). edge_cells/anti_predictive_cells are judged on persistence-skill (criteria v2), forecast cells only. Triggers (casual questions too): "how accurate are your predictions?", "예측 잘 맞아?", "track record 있어?", "can I trust these forecasts?", "적중률 보여줘", "does macro actually predict these markets?". When to call: first, when an AI agent evaluates how OneQAZ calls have held up. Prerequisites: none. Next steps: get_ledger_integrity (tamper-evidence for these numbers), granularity="monthly" (time series), get_signal_calibration (Level-1 signal confidence reliability). Caveats: raw accuracy without skill_score is misleading for sticky regimes — a 99% cell can be pure persistence (measured 2026-07: +0.05pp over null). Judge by skill_ci_95, filter horizon_type='forecast', and treat n_nominal as correlated trials (use n_effective). Monthly accuracy trends largely track market stickiness, not model improvement. Output nature: Past calls and their realized outcomes, judged after the fact, with sample sizes and baselines. Past hit rates describe the past, not future outcomes.

Input Schema

NameRequiredDescriptionDefault
limitNoMaximum number of cells to return (response carries total/returned/truncated).
compactNoCompact view (default true): per cell only the baselined hit-rate object plus lifecycle and skill; methodology, known_biases and ledger_health become pointers. false returns every field.
categoryNoOptional macro category filter (bonds, forex, vix, commodities, credit, liquidity, inflation, energy)
granularityNocell (default) = per-cell hit rates with baselines; monthly = monthly accuracy time series per (category, target_market, lag_bucket) — compact / forecast_only / limit do not apply.cell
forecast_onlyNoOnly forecast cells (exclude nowcast). Default false.
target_marketNoOptional target market filter (coin_market, kr_market, us_market). Aliases coin/kr/us and any letter case are accepted.

Output 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. Changed2 schema fields changed
    • addedInput schema / properties / granularity
      Added value: +{
+  "default": "cell",
+  "description": "cell (default) = per-cell hit rates with baselines; monthly = monthly accuracy time series per (category, target_market, lag_bucket) — compact / forecast_only / limit do not apply.",
+  "enum": [
+    "cell",
+    "monthly"
+  ],
+  "type": "string"
+}
    • changedOutput schema / properties / full_data / anyOf
      Previous value: -[
-  {
-    "additionalProperties": true,
-    "description": "`full_data` for get_prediction_accuracy.",
-    "properties": {
-      "meta": {
-        "additionalProperties": true,
-        "properties": {
-          "baseline_accuracy": {
-            "type": "number"
-          },
-          "interpretation": {
-            "type": "string"
-          },
-          "sample_count_filter": {
-            "type": "string"
-          },
-          "source": {
-            "type": "string"
-          },
-          "total_category_target_lag_cells": {
-            "type": "integer"
-          },
-          "total_samples": {
-            "type": "integer"
-          }
-        },
-        "required": [
-          "total_category_target_lag_cells",
-          "total_samples",
-          "sample_count_filter",
-          "source",
-          "baseline_accuracy",
-          "interpretation"
-        ],
-        "type": "object"
-      },
-      "summary": {
-        "additionalProperties": {
-          "additionalProperties": {
-            "additionalProperties": {
-              "additionalProperties": true,
-              "type": "object"
-            },
-            "type": "object"
-          },
-          "type": "object"
-        },
-        "type": "object"
-      }
-    },
-    "required": [
-      "summary",
-      "meta"
-    ],
-    "type": "object"
-  },
-  {
-    "type": "null"
-  }
-]New value: +[
+  {
+    "additionalProperties": true,
+    "description": "`full_data` for get_prediction_accuracy.",
+    "properties": {
+      "meta": {
+        "additionalProperties": true,
+        "properties": {
+          "baseline_accuracy": {
+            "type": "number"
+          },
+          "interpretation": {
+            "type": "string"
+          },
+          "sample_count_filter": {
+            "type": "string"
+          },
+          "source": {
+            "type": "string"
+          },
+          "total_category_target_lag_cells": {
+            "type": "integer"
+          },
+          "total_samples": {
+            "type": "integer"
+          }
+        },
+        "required": [
+          "total_category_target_lag_cells",
+          "total_samples",
+          "sample_count_filter",
+          "source",
+          "baseline_accuracy",
+          "interpretation"
+        ],
+        "type": "object"
+      },
+      "summary": {
+        "additionalProperties": {
+          "additionalProperties": {
+            "additionalProperties": {
+              "additionalProperties": true,
+              "type": "object"
+            },
+            "type": "object"
+          },
+          "type": "object"
+        },
+        "type": "object"
+      }
+    },
+    "required": [
+      "summary",
+      "meta"
+    ],
+    "type": "object"
+  },
+  {
+    "additionalProperties": true,
+    "description": "`full_data` for get_monthly_accuracy_trend.",
+    "properties": {
+      "meta": {
+        "additionalProperties": true,
+        "type": "object"
+      },
+      "trend": {
+        "items": {
+          "additionalProperties": true,
+          "properties": {
+            "accuracy": {
+              "anyOf": [
+                {
+                  "type": "number"
+                },
+                {
+                  "type": "null"
+                }
+              ],
+              "default": null
+            },
+            "category": {
+              "anyOf": [
+                {
+                  "type": "string"
+                },
+                {
+                  "type": "null"
+                }
+              ],
+              "default": null
+            },
+            "lag_bucket": {
+              "anyOf": [
+                {
+                  "type": "string"
+                },
+                {
+                  "type": "null"
+                }
+              ],
+              "default": null
+            },
+            "month": {
+              "anyOf": [
+                {
+                  "type": "string"
+                },
+                {
+                  "type": "null"
+                }
+              ],
+              "default": null
+            },
+            "sample_count": {
+              "anyOf": [
+                {
+                  "type": "integer"
+                },
+                {
+                  "type": "null"
+                }
+              ],
+              "default": null
+            },
+            "target_market": {
+              "anyOf": [
+                {
+                  "type": "string"
+                },
+                {
+                  "type": "null"
+                }
+              ],
+              "default": null
+            }
+          },
+          "type": "object"
+        },
+        "type": "array"
+      }
+    },
+    "type": "object"
+  },
+  {
+    "type": "null"
+  }
+]
  2. Changed3 schema fields changed
    • addedInput schema / properties / compact
      Added value: +{
+  "default": true,
+  "description": "Compact view (default true): per cell only the baselined hit-rate object plus lifecycle and skill; methodology, known_biases and ledger_health become pointers. false returns every field.",
+  "type": "boolean"
+}
    • addedInput schema / properties / forecast_only
      Added value: +{
+  "default": false,
+  "description": "Only forecast cells (exclude nowcast). Default false.",
+  "type": "boolean"
+}
    • addedInput schema / properties / limit
      Added value: +{
+  "anyOf": [
+    {
+      "maximum": 200,
+      "minimum": 0,
+      "type": "integer"
+    },
+    {
+      "type": "null"
+    }
+  ],
+  "default": null,
+  "description": "Maximum number of cells to return (response carries total/returned/truncated)."
+}
  3. Changed1 schema field changed
    • addedInput schema / additionalProperties
      Added value: +false
  4. Changed17 schema fields changed
    • removedOutput schema / properties / _followup_questions_for_user
      Removed value: -{
-  "anyOf": [
-    {
-      "items": {
-        "type": "string"
-      },
-      "type": "array"
-    },
-    {
-      "type": "null"
-    }
-  ],
-  "default": null
-}
    • removedOutput schema / properties / _llm_summary
      Removed value: -{
-  "anyOf": [
-    {
-      "type": "string"
-    },
-    {
-      "type": "null"
-    }
-  ],
-  "default": null
-}
    • removedOutput schema / properties / _market_state_narrative
      Removed value: -{
-  "anyOf": [
-    {
-      "additionalProperties": true,
-      "description": "Wrapper for `_market_state_narrative` — bilingual + provenance.",
-      "properties": {
-        "_source": {
-          "anyOf": [
-            {
-              "type": "string"
-            },
-            {
-              "type": "null"
-            }
-          ],
-          "default": null
-        },
-        "en": {
-          "anyOf": [
-            {
-              "additionalProperties": true,
-              "description": "Bilingual narrative — one of {ko, en} must carry a headline.",
-              "properties": {
-                "evidence": {
-                  "items": {
-                    "type": "string"
-                  },
-                  "type": "array"
-                },
-                "headline": {
-                  "type": "string"
-                },
-                "what_to_watch": {
-                  "anyOf": [
-                    {
-                      "type": "string"
-                    },
-                    {
-                      "type": "null"
-                    }
-                  ],
-                  "default": null
-                }
-              },
-              "required": [
-                "headline"
-              ],
-              "type": "object"
-            },
-            {
-              "type": "null"
-            }
-          ],
-          "default": null
-        },
-        "ko": {
-          "anyOf": [
-            {
-              "additionalProperties": true,
-              "description": "Bilingual narrative — one of {ko, en} must carry a headline.",
-              "properties": {
-                "evidence": {
-                  "items": {
-                    "type": "string"
-                  },
-                  "type": "array"
-                },
-                "headline": {
-                  "type": "string"
-                },
-                "what_to_watch": {
-                  "anyOf": [
-                    {
-                      "type": "string"
-                    },
-                    {
-                      "type": "null"
-                    }
-                  ],
-                  "default": null
-                }
-              },
-              "required": [
-                "headline"
-              ],
-              "type": "object"
-            },
-            {
-              "type": "null"
-            }
-          ],
-          "default": null
-        }
-      },
-      "type": "object"
-    },
-    {
-      "type": "null"
-    }
-  ],
-  "default": null
-}
    • removedOutput schema / properties / _next_actions
      Removed value: -{
-  "anyOf": [
-    {
-      "items": {
-        "additionalProperties": true,
-        "description": "One AI-actionable follow-up call recommendation.",
-        "properties": {
-          "args": {
-            "additionalProperties": true,
-            "type": "object"
-          },
-          "intent": {
-            "description": "Short intent label, max ~120 chars",
-            "type": "string"
-          },
-          "priority": {
-            "default": "normal",
-            "enum": [
-              "high",
-              "normal",
-              "low"
-            ],
-            "type": "string"
-          },
-          "rationale": {
-            "default": "",
-            "description": "Why this is recommended",
-            "type": "string"
-          },
-          "tool": {
-            "description": "Recommended tool name to invoke next",
-            "type": "string"
-          }
-        },
-        "required": [
-          "intent",
-          "tool"
-        ],
-        "type": "object"
-      },
-      "type": "array"
-    },
-    {
-      "type": "null"
-    }
-  ],
-  "default": null
-}
    • removedOutput schema / properties / _value_signals
      Removed value: -{
-  "anyOf": [
-    {
-      "additionalProperties": true,
-      "description": "Static product/value metadata — same for every response of a tool type.",
-      "properties": {
-        "data_freshness_seconds": {
-          "default": 120,
-          "type": "integer"
-        },
-        "key_signup_url": {
-          "default": "https://api.oneqaz.com/keys",
-          "type": "string"
-        },
-        "pricing_url": {
-          "default": "https://api.oneqaz.com/pricing",
-          "type": "string"
-        },
-        "schema_version": {
-          "default": "1.1",
-          "type": "string"
-        },
-        "self_correcting": {
-          "default": true,
-          "type": "boolean"
-        },
-        "tier_default": {
-          "default": "free",
-          "enum": [
-            "free",
-            "pro",
-            "internal"
-          ],
-          "type": "string"
-        },
-        "tier_default_limits": {
-          "additionalProperties": {
-            "type": "integer"
-          },
-          "type": "object"
-        },
-        "what_pro_unlocks": {
-          "default": "33x daily quota (50K), 3.3x burst (200/min) — same tools, higher volume",
-          "type": "string"
-        }
-      },
-      "type": "object"
-    },
-    {
-      "type": "null"
-    }
-  ],
-  "default": null
-}
    • removedOutput schema / properties / action
      Removed value: -{
-  "anyOf": [
-    {
-      "type": "string"
-    },
-    {
-      "type": "null"
-    }
-  ],
-  "default": null,
-  "description": "Recommended client action (error path)"
-}
    • removedOutput schema / properties / action_value
      Removed value: -{
-  "anyOf": [
-    {
-      "type": "string"
-    },
-    {
-      "type": "null"
-    }
-  ],
-  "default": null
-}
    • removedOutput schema / properties / ai_summary
      Removed value: -{
-  "anyOf": [
-    {
-      "type": "string"
-    },
-    {
-      "type": "null"
-    }
-  ],
-  "default": null,
-  "description": "One-line AI-oriented summary (success path)"
-}
    • removedOutput schema / properties / ai_summary_generated_at
      Removed value: -{
-  "anyOf": [
-    {
-      "type": "string"
-    },
-    {
-      "type": "null"
-    }
-  ],
-  "default": null,
-  "description": "RFC3339 UTC"
-}
    • removedOutput schema / properties / ai_summary_ttl_seconds
      Removed value: -{
-  "anyOf": [
-    {
-      "minimum": 0,
-      "type": "integer"
-    },
-    {
-      "type": "null"
-    }
-  ],
-  "default": null
-}
    • removedOutput schema / properties / error
      Removed value: -{
-  "anyOf": [
-    {
-      "type": "boolean"
-    },
-    {
-      "type": "null"
-    }
-  ],
-  "default": null,
-  "description": "Set true on error responses"
-}
    • removedOutput schema / properties / error_code
      Removed value: -{
-  "anyOf": [
-    {
-      "type": "string"
-    },
-    {
-      "type": "null"
-    }
-  ],
-  "default": null,
-  "description": "Stable error identifier; see mcp_error_policy.md"
-}
    • removedOutput schema / properties / fallback_note
      Removed value: -{
-  "anyOf": [
-    {
-      "type": "string"
-    },
-    {
-      "type": "null"
-    }
-  ],
-  "default": null
-}
    • removedOutput schema / properties / fallback_tool
      Removed value: -{
-  "anyOf": [
-    {
-      "type": "string"
-    },
-    {
-      "type": "null"
-    }
-  ],
-  "default": null,
-  "description": "Suggested fallback (error path)"
-}
    • removedOutput schema / properties / reason
      Removed value: -{
-  "anyOf": [
-    {
-      "type": "string"
-    },
-    {
-      "type": "null"
-    }
-  ],
-  "default": null,
-  "description": "Human-readable cause (error path)"
-}
    • removedOutput schema / properties / retryable
      Removed value: -{
-  "anyOf": [
-    {
-      "type": "boolean"
-    },
-    {
-      "type": "null"
-    }
-  ],
-  "default": null,
-  "description": "Whether the client should retry (error path)"
-}
    • removedOutput schema / properties / summary_for_user
      Removed value: -{
-  "anyOf": [
-    {
-      "type": "string"
-    },
-    {
-      "type": "null"
-    }
-  ],
-  "default": null,
-  "description": "One-line jargon-free Korean summary (success path)"
-}
  5. Changed7 schema fields changed
    • addedInput schema / properties / category / anyOf
      Added value: +[
+  {
+    "type": "string"
+  },
+  {
+    "type": "null"
+  }
+]
    • addedInput schema / properties / category / description
      Added value: +"Optional macro category filter (bonds, forex, vix, commodities, credit, liquidity, inflation, energy)"
    • removedInput schema / properties / category / type
      Removed value: -"string"
    • addedInput schema / properties / target_market / anyOf
      Added value: +[
+  {
+    "type": "string"
+  },
+  {
+    "type": "null"
+  }
+]
    • addedInput schema / properties / target_market / description
      Added value: +"Optional target market filter (coin_market, kr_market, us_market). Aliases coin/kr/us and any letter case are accepted."
    • addedInput schema / properties / target_market / enum
      Added value: +[
+  "crypto",
+  "kr_stock",
+  "us_stock"
+]
    • removedInput schema / properties / target_market / type
      Removed value: -"string"
  6. Changed1 schema field changed
    • changedOutput schema / properties / _value_signals / anyOf
      Previous value: -[
-  {
-    "additionalProperties": true,
-    "description": "Static product/value metadata — same for every response of a tool type.",
-    "properties": {
-      "data_freshness_seconds": {
-        "default": 120,
-        "type": "integer"
-      },
-      "key_signup_url": {
-        "default": "https://api.oneqaz.com/keys",
-        "type": "string"
-      },
-      "pricing_url": {
-        "default": "https://api.oneqaz.com/pricing",
-        "type": "string"
-      },
-      "schema_version": {
-        "default": "1.0",
-        "type": "string"
-      },
-      "self_correcting": {
-        "default": true,
-        "type": "boolean"
-      },
-      "tier_default": {
-        "default": "free",
-        "enum": [
-          "free",
-          "pro",
-          "internal"
-        ],
-        "type": "string"
-      },
-      "tier_default_limits": {
-        "additionalProperties": {
-          "type": "integer"
-        },
-        "type": "object"
-      },
-      "what_pro_unlocks": {
-        "default": "33x daily quota (50K), 3.3x burst (200/min) — same tools, higher volume",
-        "type": "string"
-      }
-    },
-    "type": "object"
-  },
-  {
-    "type": "null"
-  }
-]New value: +[
+  {
+    "additionalProperties": true,
+    "description": "Static product/value metadata — same for every response of a tool type.",
+    "properties": {
+      "data_freshness_seconds": {
+        "default": 120,
+        "type": "integer"
+      },
+      "key_signup_url": {
+        "default": "https://api.oneqaz.com/keys",
+        "type": "string"
+      },
+      "pricing_url": {
+        "default": "https://api.oneqaz.com/pricing",
+        "type": "string"
+      },
+      "schema_version": {
+        "default": "1.1",
+        "type": "string"
+      },
+      "self_correcting": {
+        "default": true,
+        "type": "boolean"
+      },
+      "tier_default": {
+        "default": "free",
+        "enum": [
+          "free",
+          "pro",
+          "internal"
+        ],
+        "type": "string"
+      },
+      "tier_default_limits": {
+        "additionalProperties": {
+          "type": "integer"
+        },
+        "type": "object"
+      },
+      "what_pro_unlocks": {
+        "default": "33x daily quota (50K), 3.3x burst (200/min) — same tools, higher volume",
+        "type": "string"
+      }
+    },
+    "type": "object"
+  },
+  {
+    "type": "null"
+  }
+]
  7. Changed1 schema field changed
    • changedOutput schema / properties / _value_signals / anyOf
      Previous value: -[
-  {
-    "additionalProperties": true,
-    "description": "Static product/value metadata — same for every response of a tool type.",
-    "properties": {
-      "data_freshness_seconds": {
-        "default": 120,
-        "type": "integer"
-      },
-      "key_signup_url": {
-        "default": "https://oneqaz.com/keys",
-        "type": "string"
-      },
-      "pricing_url": {
-        "default": "https://oneqaz.com/pricing",
-        "type": "string"
-      },
-      "schema_version": {
-        "default": "1.0",
-        "type": "string"
-      },
-      "self_correcting": {
-        "default": true,
-        "type": "boolean"
-      },
-      "tier_default": {
-        "default": "free",
-        "enum": [
-          "free",
-          "pro",
-          "internal"
-        ],
-        "type": "string"
-      },
-      "tier_default_limits": {
-        "additionalProperties": {
-          "type": "integer"
-        },
-        "type": "object"
-      },
-      "what_pro_unlocks": {
-        "default": "33x daily quota (50K), 3.3x burst (200/min) — same tools, higher volume",
-        "type": "string"
-      }
-    },
-    "type": "object"
-  },
-  {
-    "type": "null"
-  }
-]New value: +[
+  {
+    "additionalProperties": true,
+    "description": "Static product/value metadata — same for every response of a tool type.",
+    "properties": {
+      "data_freshness_seconds": {
+        "default": 120,
+        "type": "integer"
+      },
+      "key_signup_url": {
+        "default": "https://api.oneqaz.com/keys",
+        "type": "string"
+      },
+      "pricing_url": {
+        "default": "https://api.oneqaz.com/pricing",
+        "type": "string"
+      },
+      "schema_version": {
+        "default": "1.0",
+        "type": "string"
+      },
+      "self_correcting": {
+        "default": true,
+        "type": "boolean"
+      },
+      "tier_default": {
+        "default": "free",
+        "enum": [
+          "free",
+          "pro",
+          "internal"
+        ],
+        "type": "string"
+      },
+      "tier_default_limits": {
+        "additionalProperties": {
+          "type": "integer"
+        },
+        "type": "object"
+      },
+      "what_pro_unlocks": {
+        "default": "33x daily quota (50K), 3.3x burst (200/min) — same tools, higher volume",
+        "type": "string"
+      }
+    },
+    "type": "object"
+  },
+  {
+    "type": "null"
+  }
+]
  8. Changed2 schema fields changed
    • addedOutput schema / properties
      Added value: +{
+  "_followup_questions_for_user": {
+    "anyOf": [
+      {
+        "items": {
+          "type": "string"
+        },
+        "type": "array"
+      },
+      {
+        "type": "null"
+      }
+    ],
+    "default": null
+  },
+  "_llm_summary": {
+    "anyOf": [
+      {
+        "type": "string"
+      },
+      {
+        "type": "null"
+      }
+    ],
+    "default": null
+  },
+  "_market_state_narrative": {
+    "anyOf": [
+      {
+        "additionalProperties": true,
+        "description": "Wrapper for `_market_state_narrative` — bilingual + provenance.",
+        "properties": {
+          "_source": {
+            "anyOf": [
+              {
+                "type": "string"
+              },
+              {
+                "type": "null"
+              }
+            ],
+            "default": null
+          },
+          "en": {
+            "anyOf": [
+              {
+                "additionalProperties": true,
+                "description": "Bilingual narrative — one of {ko, en} must carry a headline.",
+                "properties": {
+                  "evidence": {
+                    "items": {
+                      "type": "string"
+                    },
+                    "type": "array"
+                  },
+                  "headline": {
+                    "type": "string"
+                  },
+                  "what_to_watch": {
+                    "anyOf": [
+                      {
+                        "type": "string"
+                      },
+                      {
+                        "type": "null"
+                      }
+                    ],
+                    "default": null
+                  }
+                },
+                "required": [
+                  "headline"
+                ],
+                "type": "object"
+              },
+              {
+                "type": "null"
+              }
+            ],
+            "default": null
+          },
+          "ko": {
+            "anyOf": [
+              {
+                "additionalProperties": true,
+                "description": "Bilingual narrative — one of {ko, en} must carry a headline.",
+                "properties": {
+                  "evidence": {
+                    "items": {
+                      "type": "string"
+                    },
+                    "type": "array"
+                  },
+                  "headline": {
+                    "type": "string"
+                  },
+                  "what_to_watch": {
+                    "anyOf": [
+                      {
+                        "type": "string"
+                      },
+                      {
+                        "type": "null"
+                      }
+                    ],
+                    "default": null
+                  }
+                },
+                "required": [
+                  "headline"
+                ],
+                "type": "object"
+              },
+              {
+                "type": "null"
+              }
+            ],
+            "default": null
+          }
+        },
+        "type": "object"
+      },
+      {
+        "type": "null"
+      }
+    ],
+    "default": null
+  },
+  "_next_actions": {
+    "anyOf": [
+      {
+        "items": {
+          "additionalProperties": true,
+          "description": "One AI-actionable follow-up call recommendation.",
+          "properties": {
+            "args": {
+              "additionalProperties": true,
+              "type": "object"
+            },
+            "intent": {
+              "description": "Short intent label, max ~120 chars",
+              "type": "string"
+            },
+            "priority": {
+              "default": "normal",
+              "enum": [
+                "high",
+                "normal",
+                "low"
+              ],
+              "type": "string"
+            },
+            "rationale": {
+              "default": "",
+              "description": "Why this is recommended",
+              "type": "string"
+            },
+            "tool": {
+              "description": "Recommended tool name to invoke next",
+              "type": "string"
+            }
+          },
+          "required": [
+            "intent",
+            "tool"
+          ],
+          "type": "object"
+        },
+        "type": "array"
+      },
+      {
+        "type": "null"
+      }
+    ],
+    "default": null
+  },
+  "_value_signals": {
+    "anyOf": [
+      {
+        "additionalProperties": true,
+        "description": "Static product/value metadata — same for every response of a tool type.",
+        "properties": {
+          "data_freshness_seconds": {
+            "default": 120,
+            "type": "integer"
+          },
+          "key_signup_url": {
+            "default": "https://oneqaz.com/keys",
+            "type": "string"
+          },
+          "pricing_url": {
+            "default": "https://oneqaz.com/pricing",
+            "type": "string"
+          },
+          "schema_version": {
+            "default": "1.0",
+            "type": "string"
+          },
+          "self_correcting": {
+            "default": true,
+            "type": "boolean"
+          },
+          "tier_default": {
+            "default": "free",
+            "enum": [
+              "free",
+              "pro",
+              "internal"
+            ],
+            "type": "string"
+          },
+          "tier_default_limits": {
+            "additionalProperties": {
+              "type": "integer"
+            },
+            "type": "object"
+          },
+          "what_pro_unlocks": {
+            "default": "33x daily quota (50K), 3.3x burst (200/min) — same tools, higher volume",
+            "type": "string"
+          }
+        },
+        "type": "object"
+      },
+      {
+        "type": "null"
+      }
+    ],
+    "default": null
+  },
+  "action": {
+    "anyOf": [
+      {
+        "type": "string"
+      },
+      {
+        "type": "null"
+      }
+    ],
+    "default": null,
+    "description": "Recommended client action (error path)"
+  },
+  "action_value": {
+    "anyOf": [
+      {
+        "type": "string"
+      },
+      {
+        "type": "null"
+      }
+    ],
+    "default": null
+  },
+  "ai_summary": {
+    "anyOf": [
+      {
+        "type": "string"
+      },
+      {
+        "type": "null"
+      }
+    ],
+    "default": null,
+    "description": "One-line AI-oriented summary (success path)"
+  },
+  "ai_summary_generated_at": {
+    "anyOf": [
+      {
+        "type": "string"
+      },
+      {
+        "type": "null"
+      }
+    ],
+    "default": null,
+    "description": "RFC3339 UTC"
+  },
+  "ai_summary_ttl_seconds": {
+    "anyOf": [
+      {
+        "minimum": 0,
+        "type": "integer"
+      },
+      {
+        "type": "null"
+      }
+    ],
+    "default": null
+  },
+  "data_classification": {
+    "anyOf": [
+      {
+        "const": "research_information_only",
+        "type": "string"
+      },
+      {
+        "type": "null"
+      }
+    ],
+    "default": null
+  },
+  "disclaimer": {
+    "description": "Canonical compliance disclaimer (always present)",
+    "type": "string"
+  },
+  "error": {
+    "anyOf": [
+      {
+        "type": "boolean"
+      },
+      {
+        "type": "null"
+      }
+    ],
+    "default": null,
+    "description": "Set true on error responses"
+  },
+  "error_code": {
+    "anyOf": [
+      {
+        "type": "string"
+      },
+      {
+        "type": "null"
+      }
+    ],
+    "default": null,
+    "description": "Stable error identifier; see mcp_error_policy.md"
+  },
+  "fallback_note": {
+    "anyOf": [
+      {
+        "type": "string"
+      },
+      {
+        "type": "null"
+      }
+    ],
+    "default": null
+  },
+  "fallback_tool": {
+    "anyOf": [
+      {
+        "type": "string"
+      },
+      {
+        "type": "null"
+      }
+    ],
+    "default": null,
+    "description": "Suggested fallback (error path)"
+  },
+  "full_data": {
+    "anyOf": [
+      {
+        "additionalProperties": true,
+        "description": "`full_data` for get_prediction_accuracy.",
+        "properties": {
+          "meta": {
+            "additionalProperties": true,
+            "properties": {
+              "baseline_accuracy": {
+                "type": "number"
+              },
+              "interpretation": {
+                "type": "string"
+              },
+              "sample_count_filter": {
+                "type": "string"
+              },
+              "source": {
+                "type": "string"
+              },
+              "total_category_target_lag_cells": {
+                "type": "integer"
+              },
+              "total_samples": {
+                "type": "integer"
+              }
+            },
+            "required": [
+              "total_category_target_lag_cells",
+              "total_samples",
+              "sample_count_filter",
+              "source",
+              "baseline_accuracy",
+              "interpretation"
+            ],
+            "type": "object"
+          },
+          "summary": {
+            "additionalProperties": {
+              "additionalProperties": {
+                "additionalProperties": {
+                  "additionalProperties": true,
+                  "type": "object"
+                },
+                "type": "object"
+              },
+              "type": "object"
+            },
+            "type": "object"
+          }
+        },
+        "required": [
+          "summary",
+          "meta"
+        ],
+        "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
+  },
+  "reason": {
+    "anyOf": [
+      {
+        "type": "string"
+      },
+      {
+        "type": "null"
+      }
+    ],
+    "default": null,
+    "description": "Human-readable cause (error path)"
+  },
+  "request_id": {
+    "description": "32-hex per-response correlation id",
+    "type": "string"
+  },
+  "retryable": {
+    "anyOf": [
+      {
+        "type": "boolean"
+      },
+      {
+        "type": "null"
+      }
+    ],
+    "default": null,
+    "description": "Whether the client should retry (error path)"
+  },
+  "summary_for_user": {
+    "anyOf": [
+      {
+        "type": "string"
+      },
+      {
+        "type": "null"
+      }
+    ],
+    "default": null,
+    "description": "One-line jargon-free Korean summary (success path)"
+  },
+  "timestamp": {
+    "description": "RFC3339 UTC, server build time",
+    "type": "string"
+  }
+}
    • addedOutput schema / required
      Added value: +[
+  "disclaimer",
+  "request_id",
+  "timestamp"
+]
  9. First observed

TDQS

A4.7/5.0
Behavior5/5

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

Annotations already cover readOnly/idempotent/closed-world, yet the description adds substantive behavioral context: that raw accuracy mostly measures regime persistence, that a 99% cell can be pure persistence (+0.05pp over null), the 2026-07-08 methodology cutover behind accuracy_v2_only, and that n_nominal should be treated as correlated trials. It also closes with an 'output nature' statement framing results as retrospective.

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?

Front-loaded and information-dense, but padded by restatement: 'Call this first when judging how OneQAZ's macro calls have held up' is repeated almost verbatim under 'When to call'. The stitched multi-section layout with wrapped lines makes it longer than the payload warrants.

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 values need not be explained, and the description still covers the interpretive caveats an agent needs (skill_ci_95 judging, n_effective, persistence baselines, monthly trend caveat). Nothing required to call this correctly on a 6-parameter, zero-required tool is missing.

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?

Schema coverage is 100%, so the baseline is 3, but the description adds real meaning: granularity="monthly" is called out twice and correctly noted as overriding compact/limit. One flaw: it advises 'filter horizon_type=\'forecast\'' whereas the actual parameter is the boolean forecast_only, a slight parameter-naming mismatch.

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 verb and resource: per-cell (category, target_market, lag_bucket) hit rates with honest baselines, plus a monthly time-series mode. It explicitly distinguishes itself from siblings get_ledger_integrity (tamper evidence) and get_signal_calibration (Level-1 signal reliability), so an agent can route correctly without opening a schema.

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?

Gives explicit when-to-call ('first, when an AI agent evaluates how OneQAZ calls have held up'), prerequisites ('none'), concrete natural-language triggers including Korean phrasings, and named next steps to alternatives. This is about as complete a routing block as a tool description can carry.

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