Quantified Self MCP Server

Overview Schema Source Related Servers Discussions Admin

Find correlation between two metrics

find_metric_correlation

Read-onlyIdempotent

Compute Pearson correlation between two metrics over a specified window, joined by date, with optional lag, to check if they move together. Correlation, not causation.

Instructions

Compute the Pearson correlation between two metrics over the same window, joined by date. Correlation, not causation: a strong r just means the two moved together, not that one caused the other.

Use this tool when:

the user names or implies two different metrics and asks whether they move together (e.g. "does my sleep affect my mood?", "did my HRV change after I increased my workouts?").

Do not use this tool when:

only one metric is in question -> use get_baseline, calculate_metric_trend, or detect_metric_anomalies instead, depending on what's being asked about that one metric.

Privacy note: this server and its SQLite file are entirely local, but the data returned by this tool becomes part of the conversation sent to whatever model the calling client is configured with. If that model runs in the cloud rather than on your machine, treat this the same as pasting the data into a chat with that provider.

Input Schema

TableJSON Schema

Name	Required	Description
`end_date`	No	Last day to include, formatted YYYY-MM-DD. Defaults to today.
`lag_days`	No	Shift metric_b this many days later before joining — 1 tests whether metric_a today predicts metric_b tomorrow (e.g. "does poor sleep tonight predict lower steps tomorrow?"). 0 (default) compares same-day values.
`metric_a`	Yes
`metric_b`	Yes
`start_date`	No	First day to include, formatted YYYY-MM-DD. Defaults to 90 days before end_date.

Output Schema

TableJSON Schema

Name	Required	Description
`n`	Yes
`r`	No
`note`	No
`claim`	Yes	Evidence and decision for the correlation claim; read claim.decision before reporting it.
`lag_days`	Yes
`metric_a`	Yes
`metric_b`	Yes
`evidence_a`	Yes	DEPRECATED: identical to claim.evidence_a. Use claim.decision, not a standalone confidence field.
`evidence_b`	Yes	DEPRECATED: identical to claim.evidence_b. Use claim.decision, not a standalone confidence field.

Schema Changelog

Changes observed during successful MCP inspections.

Changed3 schema fields changedv1.0.28Sep 30, 2026

removedOutput schema / properties / claim_decision

Removed value: -{
-  "deprecated": true,
-  "description": "DEPRECATED: identical to claim.decision. Use claim.decision instead.",
-  "properties": {
-    "must_state": {
-      "items": {
-        "type": "string"
-      },
-      "type": "array"
-    },
-    "permitted_phrasing_class": {
-      "type": "string"
-    },
-    "template": {
-      "type": "string"
-    },
-    "tier": {
-      "type": "string"
-    }
-  },
-  "required": [
-    "tier",
-    "permitted_phrasing_class",
-    "must_state",
-    "template"
-  ],
-  "type": "object"
-}

removedOutput schema / properties / evidence_profile

Removed value: -{
-  "deprecated": true,
-  "description": "DEPRECATED: identical to claim.profile. Use claim.decision instead.",
-  "properties": {
-    "analysis": {
-      "type": "string"
-    },
-    "dimensions": {
-      "items": {
-        "properties": {
-          "can_block": {
-            "default": true,
-            "type": "boolean"
-          },
-          "details": {
-            "additionalProperties": true,
-            "type": "object"
-          },
-          "dimension": {
-            "enum": [
-              "sample",
-              "temporal",
-              "robustness",
-              "missingness",
-              "practical",
-              "measurement_validity",
-              "provenance"
-            ],
-            "type": "string"
-          },
-          "reason_codes": {
-            "items": {
-              "type": "string"
-            },
-            "type": "array"
-          },
-          "status": {
-            "enum": [
-              "adequate",
-              "negligible",
-              "not_assessed",
-              "weak",
-              "concern",
-              "blocking"
-            ],
-            "type": "string"
-          }
-        },
-        "required": [
-          "dimension",
-          "status"
-        ],
-        "type": "object"
-      },
-      "type": "array"
-    },
-    "effect": {
-      "additionalProperties": true,
-      "type": "object"
-    },
-    "metric": {
-      "type": "string"
-    }
-  },
-  "required": [
-    "metric",
-    "analysis",
-    "dimensions"
-  ],
-  "type": "object"
-}

changedOutput schema / required

Previous value: -[
-  "metric_a",
-  "metric_b",
-  "lag_days",
-  "n",
-  "claim",
-  "evidence_a",
-  "evidence_b",
-  "evidence_profile",
-  "claim_decision"
-]New value: +[
+  "metric_a",
+  "metric_b",
+  "lag_days",
+  "n",
+  "claim",
+  "evidence_a",
+  "evidence_b"
+]

Changed21 schema fields changedv1.0.26Sep 25, 2026

addedOutput schema / properties / claim

Added value: +{
+  "description": "Evidence and decision for the correlation claim; read claim.decision before reporting it.",
+  "properties": {
+    "decision": {
+      "description": "How strongly this claim may be stated. tier is insufficient, suggestive, detectable_not_meaningful or supported; every entry in must_state has to be mentioned when reporting it.",
+      "properties": {
+        "must_state": {
+          "items": {
+            "type": "string"
+          },
+          "type": "array"
+        },
+        "permitted_phrasing_class": {
+          "type": "string"
+        },
+        "template": {
+          "type": "string"
+        },
+        "tier": {
+          "type": "string"
+        }
+      },
+      "required": [
+        "tier",
+        "permitted_phrasing_class",
+        "must_state",
+        "template"
+      ],
+      "type": "object"
+    },
+    "evidence_a": {
+      "description": "Descriptive data coverage behind the first source.",
+      "properties": {
+        "confidence": {
+          "type": "string"
+        },
+        "coverage_ratio": {
+          "type": "number"
+        },
+        "expected_days": {
+          "type": "integer"
+        },
+        "freshness_days": {
+          "anyOf": [
+            {
+              "type": "integer"
+            },
+            {
+              "type": "null"
+            }
+          ],
+          "default": null
+        },
+        "gaps": {
+          "items": {
+            "properties": {
+              "days": {
+                "type": "integer"
+              },
+              "end": {
+                "type": "string"
+              },
+              "start": {
+                "type": "string"
+              }
+            },
+            "required": [
+              "start",
+              "end",
+              "days"
+            ],
+            "type": "object"
+          },
+          "type": "array"
+        },
+        "measurement_count": {
+          "type": "integer"
+        },
+        "missing_days": {
+          "type": "integer"
+        },
+        "observed_days": {
+          "type": "integer"
+        },
+        "observed_end": {
+          "anyOf": [
+            {
+              "type": "string"
+            },
+            {
+              "type": "null"
+            }
+          ],
+          "default": null
+        },
+        "observed_start": {
+          "anyOf": [
+            {
+              "type": "string"
+            },
+            {
+              "type": "null"
+            }
+          ],
+          "default": null
+        },
+        "recent_gap_days": {
+          "type": "integer"
+        },
+        "requested_end": {
+          "type": "string"
+        },
+        "requested_start": {
+          "type": "string"
+        }
+      },
+      "required": [
+        "requested_start",
+        "requested_end",
+        "expected_days",
+        "observed_days",
+        "coverage_ratio",
+        "missing_days",
+        "measurement_count",
+        "gaps",
+        "recent_gap_days",
+        "confidence"
+      ],
+      "type": "object"
+    },
+    "evidence_b": {
+      "description": "Descriptive data coverage behind the second source.",
+      "properties": {
+        "confidence": {
+          "type": "string"
+        },
+        "coverage_ratio": {
+          "type": "number"
+        },
+        "expected_days": {
+          "type": "integer"
+        },
+        "freshness_days": {
+          "anyOf": [
+            {
+              "type": "integer"
+            },
+            {
+              "type": "null"
+            }
+          ],
+          "default": null
+        },
+        "gaps": {
+          "items": {
+            "properties": {
+              "days": {
+                "type": "integer"
+              },
+              "end": {
+                "type": "string"
+              },
+              "start": {
+                "type": "string"
+              }
+            },
+            "required": [
+              "start",
+              "end",
+              "days"
+            ],
+            "type": "object"
+          },
+          "type": "array"
+        },
+        "measurement_count": {
+          "type": "integer"
+        },
+        "missing_days": {
+          "type": "integer"
+        },
+        "observed_days": {
+          "type": "integer"
+        },
+        "observed_end": {
+          "anyOf": [
+            {
+              "type": "string"
+            },
+            {
+              "type": "null"
+            }
+          ],
+          "default": null
+        },
+        "observed_start": {
+          "anyOf": [
+            {
+              "type": "string"
+            },
+            {
+              "type": "null"
+            }
+          ],
+          "default": null
+        },
+        "recent_gap_days": {
+          "type": "integer"
+        },
+        "requested_end": {
+          "type": "string"
+        },
+        "requested_start": {
+          "type": "string"
+        }
+      },
+      "required": [
+        "requested_start",
+        "requested_end",
+        "expected_days",
+        "observed_days",
+        "coverage_ratio",
+        "missing_days",
+        "measurement_count",
+        "gaps",
+        "recent_gap_days",
+        "confidence"
+      ],
+      "type": "object"
+    },
+    "profile": {
+      "description": "Per-dimension evidence quality behind this claim (sample, temporal, missingness, ...), assessed jointly across both sources where relevant. Dimensions without an evaluator yet are 'not_assessed' and cap the claim, never count as adequate.",
+      "properties": {
+        "analysis": {
+          "type": "string"
+        },
+        "dimensions": {
+          "items": {
+            "properties": {
+              "can_block": {
+                "default": true,
+                "type": "boolean"
+              },
+              "details": {
+                "additionalProperties": true,
+                "type": "object"
+              },
+              "dimension": {
+                "enum": [
+                  "sample",
+                  "temporal",
+                  "robustness",
+                  "missingness",
+                  "practical",
+                  "measurement_validity",
+                  "provenance"
+                ],
+                "type": "string"
+              },
+              "reason_codes": {
+                "items": {
+                  "type": "string"
+                },
+                "type": "array"
+              },
+              "status": {
+                "enum": [
+                  "adequate",
+                  "negligible",
+                  "not_assessed",
+                  "weak",
+                  "concern",
+                  "blocking"
+                ],
+                "type": "string"
+              }
+            },
+            "required": [
+              "dimension",
+              "status"
+            ],
+            "type": "object"
+          },
+          "type": "array"
+        },
+        "effect": {
+          "additionalProperties": true,
+          "type": "object"
+        },
+        "metric": {
+          "type": "string"
+        }
+      },
+      "required": [
+        "metric",
+        "analysis",
+        "dimensions"
+      ],
+      "type": "object"
+    }
+  },
+  "required": [
+    "evidence_a",
+    "evidence_b",
+    "profile",
+    "decision"
+  ],
+  "type": "object"
+}

addedOutput schema / properties / claim_decision / deprecated
```
Added value: +true
```

changedOutput schema / properties / claim_decision / description

Previous value: -"How strongly this result may be stated. tier is insufficient, suggestive, detectable_not_meaningful or supported; every entry in must_state has to be mentioned when reporting it."New value: +"DEPRECATED: identical to claim.decision. Use claim.decision instead."

removedOutput schema / properties / evidence_a / anyOf

Removed value: -[
-  {
-    "description": "Coverage/quality of the data a single-metric analytical result is\nbased on. See evidence.build_evidence for how each field is computed.",
-    "properties": {
-      "confidence": {
-        "type": "string"
-      },
-      "coverage_ratio": {
-        "type": "number"
-      },
-      "expected_days": {
-        "type": "integer"
-      },
-      "freshness_days": {
-        "anyOf": [
-          {
-            "type": "integer"
-          },
-          {
-            "type": "null"
-          }
-        ],
-        "default": null
-      },
-      "gaps": {
-        "items": {
-          "properties": {
-            "days": {
-              "type": "integer"
-            },
-            "end": {
-              "type": "string"
-            },
-            "start": {
-              "type": "string"
-            }
-          },
-          "required": [
-            "start",
-            "end",
-            "days"
-          ],
-          "type": "object"
-        },
-        "type": "array"
-      },
-      "measurement_count": {
-        "type": "integer"
-      },
-      "missing_days": {
-        "type": "integer"
-      },
-      "observed_days": {
-        "type": "integer"
-      },
-      "observed_end": {
-        "anyOf": [
-          {
-            "type": "string"
-          },
-          {
-            "type": "null"
-          }
-        ],
-        "default": null
-      },
-      "observed_start": {
-        "anyOf": [
-          {
-            "type": "string"
-          },
-          {
-            "type": "null"
-          }
-        ],
-        "default": null
-      },
-      "recent_gap_days": {
-        "type": "integer"
-      },
-      "requested_end": {
-        "type": "string"
-      },
-      "requested_start": {
-        "type": "string"
-      }
-    },
-    "required": [
-      "requested_start",
-      "requested_end",
-      "expected_days",
-      "observed_days",
-      "coverage_ratio",
-      "missing_days",
-      "measurement_count",
-      "gaps",
-      "recent_gap_days",
-      "confidence"
-    ],
-    "type": "object"
-  },
-  {
-    "type": "null"
-  }
-]

removedOutput schema / properties / evidence_a / default
```
Removed value: -null
```
addedOutput schema / properties / evidence_a / deprecated
```
Added value: +true
```

addedOutput schema / properties / evidence_a / description

Added value: +"DEPRECATED: identical to claim.evidence_a. Use claim.decision, not a standalone confidence field."

addedOutput schema / properties / evidence_a / properties

Added value: +{
+  "confidence": {
+    "type": "string"
+  },
+  "coverage_ratio": {
+    "type": "number"
+  },
+  "expected_days": {
+    "type": "integer"
+  },
+  "freshness_days": {
+    "anyOf": [
+      {
+        "type": "integer"
+      },
+      {
+        "type": "null"
+      }
+    ],
+    "default": null
+  },
+  "gaps": {
+    "items": {
+      "properties": {
+        "days": {
+          "type": "integer"
+        },
+        "end": {
+          "type": "string"
+        },
+        "start": {
+          "type": "string"
+        }
+      },
+      "required": [
+        "start",
+        "end",
+        "days"
+      ],
+      "type": "object"
+    },
+    "type": "array"
+  },
+  "measurement_count": {
+    "type": "integer"
+  },
+  "missing_days": {
+    "type": "integer"
+  },
+  "observed_days": {
+    "type": "integer"
+  },
+  "observed_end": {
+    "anyOf": [
+      {
+        "type": "string"
+      },
+      {
+        "type": "null"
+      }
+    ],
+    "default": null
+  },
+  "observed_start": {
+    "anyOf": [
+      {
+        "type": "string"
+      },
+      {
+        "type": "null"
+      }
+    ],
+    "default": null
+  },
+  "recent_gap_days": {
+    "type": "integer"
+  },
+  "requested_end": {
+    "type": "string"
+  },
+  "requested_start": {
+    "type": "string"
+  }
+}

addedOutput schema / properties / evidence_a / required

Added value: +[
+  "requested_start",
+  "requested_end",
+  "expected_days",
+  "observed_days",
+  "coverage_ratio",
+  "missing_days",
+  "measurement_count",
+  "gaps",
+  "recent_gap_days",
+  "confidence"
+]

addedOutput schema / properties / evidence_a / type
```
Added value: +"object"
```

removedOutput schema / properties / evidence_b / anyOf

Removed value: -[
-  {
-    "description": "Coverage/quality of the data a single-metric analytical result is\nbased on. See evidence.build_evidence for how each field is computed.",
-    "properties": {
-      "confidence": {
-        "type": "string"
-      },
-      "coverage_ratio": {
-        "type": "number"
-      },
-      "expected_days": {
-        "type": "integer"
-      },
-      "freshness_days": {
-        "anyOf": [
-          {
-            "type": "integer"
-          },
-          {
-            "type": "null"
-          }
-        ],
-        "default": null
-      },
-      "gaps": {
-        "items": {
-          "properties": {
-            "days": {
-              "type": "integer"
-            },
-            "end": {
-              "type": "string"
-            },
-            "start": {
-              "type": "string"
-            }
-          },
-          "required": [
-            "start",
-            "end",
-            "days"
-          ],
-          "type": "object"
-        },
-        "type": "array"
-      },
-      "measurement_count": {
-        "type": "integer"
-      },
-      "missing_days": {
-        "type": "integer"
-      },
-      "observed_days": {
-        "type": "integer"
-      },
-      "observed_end": {
-        "anyOf": [
-          {
-            "type": "string"
-          },
-          {
-            "type": "null"
-          }
-        ],
-        "default": null
-      },
-      "observed_start": {
-        "anyOf": [
-          {
-            "type": "string"
-          },
-          {
-            "type": "null"
-          }
-        ],
-        "default": null
-      },
-      "recent_gap_days": {
-        "type": "integer"
-      },
-      "requested_end": {
-        "type": "string"
-      },
-      "requested_start": {
-        "type": "string"
-      }
-    },
-    "required": [
-      "requested_start",
-      "requested_end",
-      "expected_days",
-      "observed_days",
-      "coverage_ratio",
-      "missing_days",
-      "measurement_count",
-      "gaps",
-      "recent_gap_days",
-      "confidence"
-    ],
-    "type": "object"
-  },
-  {
-    "type": "null"
-  }
-]

removedOutput schema / properties / evidence_b / default
```
Removed value: -null
```
addedOutput schema / properties / evidence_b / deprecated
```
Added value: +true
```

addedOutput schema / properties / evidence_b / description

Added value: +"DEPRECATED: identical to claim.evidence_b. Use claim.decision, not a standalone confidence field."

addedOutput schema / properties / evidence_b / properties

Added value: +{
+  "confidence": {
+    "type": "string"
+  },
+  "coverage_ratio": {
+    "type": "number"
+  },
+  "expected_days": {
+    "type": "integer"
+  },
+  "freshness_days": {
+    "anyOf": [
+      {
+        "type": "integer"
+      },
+      {
+        "type": "null"
+      }
+    ],
+    "default": null
+  },
+  "gaps": {
+    "items": {
+      "properties": {
+        "days": {
+          "type": "integer"
+        },
+        "end": {
+          "type": "string"
+        },
+        "start": {
+          "type": "string"
+        }
+      },
+      "required": [
+        "start",
+        "end",
+        "days"
+      ],
+      "type": "object"
+    },
+    "type": "array"
+  },
+  "measurement_count": {
+    "type": "integer"
+  },
+  "missing_days": {
+    "type": "integer"
+  },
+  "observed_days": {
+    "type": "integer"
+  },
+  "observed_end": {
+    "anyOf": [
+      {
+        "type": "string"
+      },
+      {
+        "type": "null"
+      }
+    ],
+    "default": null
+  },
+  "observed_start": {
+    "anyOf": [
+      {
+        "type": "string"
+      },
+      {
+        "type": "null"
+      }
+    ],
+    "default": null
+  },
+  "recent_gap_days": {
+    "type": "integer"
+  },
+  "requested_end": {
+    "type": "string"
+  },
+  "requested_start": {
+    "type": "string"
+  }
+}

addedOutput schema / properties / evidence_b / required

Added value: +[
+  "requested_start",
+  "requested_end",
+  "expected_days",
+  "observed_days",
+  "coverage_ratio",
+  "missing_days",
+  "measurement_count",
+  "gaps",
+  "recent_gap_days",
+  "confidence"
+]

addedOutput schema / properties / evidence_b / type
```
Added value: +"object"
```
addedOutput schema / properties / evidence_profile / deprecated
```
Added value: +true
```

changedOutput schema / properties / evidence_profile / description

Previous value: -"Per-dimension evidence quality behind this result (sample, temporal, missingness, ...). Dimensions without an evaluator yet are 'not_assessed' and cap the claim, never count as adequate."New value: +"DEPRECATED: identical to claim.profile. Use claim.decision instead."

removedOutput schema / properties / sample_confidence
```
Removed value: -{
-  "type": "string"
-}
```

changedOutput schema / required

Previous value: -[
-  "evidence_profile",
-  "claim_decision",
-  "metric_a",
-  "metric_b",
-  "lag_days",
-  "n",
-  "sample_confidence"
-]New value: +[
+  "metric_a",
+  "metric_b",
+  "lag_days",
+  "n",
+  "claim",
+  "evidence_a",
+  "evidence_b",
+  "evidence_profile",
+  "claim_decision"
+]

Changed11 schema fields changedv1.0.23Sep 24, 2026

removedOutput schema / properties / claim_decision / anyOf

Removed value: -[
-  {
-    "properties": {
-      "must_state": {
-        "items": {
-          "type": "string"
-        },
-        "type": "array"
-      },
-      "permitted_phrasing_class": {
-        "type": "string"
-      },
-      "template": {
-        "type": "string"
-      },
-      "tier": {
-        "type": "string"
-      }
-    },
-    "required": [
-      "tier",
-      "permitted_phrasing_class",
-      "must_state",
-      "template"
-    ],
-    "type": "object"
-  },
-  {
-    "type": "null"
-  }
-]

removedOutput schema / properties / claim_decision / default
```
Removed value: -null
```

addedOutput schema / properties / claim_decision / properties

Added value: +{
+  "must_state": {
+    "items": {
+      "type": "string"
+    },
+    "type": "array"
+  },
+  "permitted_phrasing_class": {
+    "type": "string"
+  },
+  "template": {
+    "type": "string"
+  },
+  "tier": {
+    "type": "string"
+  }
+}

addedOutput schema / properties / claim_decision / required

Added value: +[
+  "tier",
+  "permitted_phrasing_class",
+  "must_state",
+  "template"
+]

addedOutput schema / properties / claim_decision / type
```
Added value: +"object"
```

removedOutput schema / properties / evidence_profile / anyOf

Removed value: -[
-  {
-    "properties": {
-      "analysis": {
-        "type": "string"
-      },
-      "dimensions": {
-        "items": {
-          "properties": {
-            "can_block": {
-              "default": true,
-              "type": "boolean"
-            },
-            "details": {
-              "additionalProperties": true,
-              "type": "object"
-            },
-            "dimension": {
-              "enum": [
-                "sample",
-                "temporal",
-                "robustness",
-                "missingness",
-                "practical",
-                "measurement_validity",
-                "provenance"
-              ],
-              "type": "string"
-            },
-            "reason_codes": {
-              "items": {
-                "type": "string"
-              },
-              "type": "array"
-            },
-            "status": {
-              "enum": [
-                "adequate",
-                "negligible",
-                "not_assessed",
-                "weak",
-                "concern",
-                "blocking"
-              ],
-              "type": "string"
-            }
-          },
-          "required": [
-            "dimension",
-            "status"
-          ],
-          "type": "object"
-        },
-        "type": "array"
-      },
-      "effect": {
-        "additionalProperties": true,
-        "type": "object"
-      },
-      "metric": {
-        "type": "string"
-      }
-    },
-    "required": [
-      "metric",
-      "analysis",
-      "dimensions"
-    ],
-    "type": "object"
-  },
-  {
-    "type": "null"
-  }
-]

removedOutput schema / properties / evidence_profile / default
```
Removed value: -null
```

addedOutput schema / properties / evidence_profile / properties

Added value: +{
+  "analysis": {
+    "type": "string"
+  },
+  "dimensions": {
+    "items": {
+      "properties": {
+        "can_block": {
+          "default": true,
+          "type": "boolean"
+        },
+        "details": {
+          "additionalProperties": true,
+          "type": "object"
+        },
+        "dimension": {
+          "enum": [
+            "sample",
+            "temporal",
+            "robustness",
+            "missingness",
+            "practical",
+            "measurement_validity",
+            "provenance"
+          ],
+          "type": "string"
+        },
+        "reason_codes": {
+          "items": {
+            "type": "string"
+          },
+          "type": "array"
+        },
+        "status": {
+          "enum": [
+            "adequate",
+            "negligible",
+            "not_assessed",
+            "weak",
+            "concern",
+            "blocking"
+          ],
+          "type": "string"
+        }
+      },
+      "required": [
+        "dimension",
+        "status"
+      ],
+      "type": "object"
+    },
+    "type": "array"
+  },
+  "effect": {
+    "additionalProperties": true,
+    "type": "object"
+  },
+  "metric": {
+    "type": "string"
+  }
+}

addedOutput schema / properties / evidence_profile / required

Added value: +[
+  "metric",
+  "analysis",
+  "dimensions"
+]

addedOutput schema / properties / evidence_profile / type
```
Added value: +"object"
```

changedOutput schema / required

Previous value: -[
-  "metric_a",
-  "metric_b",
-  "lag_days",
-  "n",
-  "sample_confidence"
-]New value: +[
+  "evidence_profile",
+  "claim_decision",
+  "metric_a",
+  "metric_b",
+  "lag_days",
+  "n",
+  "sample_confidence"
+]

Changed2 schema fields changedv1.0.20Sep 20, 2026

addedOutput schema / properties / claim_decision

Added value: +{
+  "anyOf": [
+    {
+      "properties": {
+        "must_state": {
+          "items": {
+            "type": "string"
+          },
+          "type": "array"
+        },
+        "permitted_phrasing_class": {
+          "type": "string"
+        },
+        "template": {
+          "type": "string"
+        },
+        "tier": {
+          "type": "string"
+        }
+      },
+      "required": [
+        "tier",
+        "permitted_phrasing_class",
+        "must_state",
+        "template"
+      ],
+      "type": "object"
+    },
+    {
+      "type": "null"
+    }
+  ],
+  "default": null,
+  "description": "How strongly this result may be stated. tier is insufficient, suggestive, detectable_not_meaningful or supported; every entry in must_state has to be mentioned when reporting it."
+}

addedOutput schema / properties / evidence_profile

Added value: +{
+  "anyOf": [
+    {
+      "properties": {
+        "analysis": {
+          "type": "string"
+        },
+        "dimensions": {
+          "items": {
+            "properties": {
+              "can_block": {
+                "default": true,
+                "type": "boolean"
+              },
+              "details": {
+                "additionalProperties": true,
+                "type": "object"
+              },
+              "dimension": {
+                "enum": [
+                  "sample",
+                  "temporal",
+                  "robustness",
+                  "missingness",
+                  "practical",
+                  "measurement_validity",
+                  "provenance"
+                ],
+                "type": "string"
+              },
+              "reason_codes": {
+                "items": {
+                  "type": "string"
+                },
+                "type": "array"
+              },
+              "status": {
+                "enum": [
+                  "adequate",
+                  "negligible",
+                  "not_assessed",
+                  "weak",
+                  "concern",
+                  "blocking"
+                ],
+                "type": "string"
+              }
+            },
+            "required": [
+              "dimension",
+              "status"
+            ],
+            "type": "object"
+          },
+          "type": "array"
+        },
+        "effect": {
+          "additionalProperties": true,
+          "type": "object"
+        },
+        "metric": {
+          "type": "string"
+        }
+      },
+      "required": [
+        "metric",
+        "analysis",
+        "dimensions"
+      ],
+      "type": "object"
+    },
+    {
+      "type": "null"
+    }
+  ],
+  "default": null,
+  "description": "Per-dimension evidence quality behind this result (sample, temporal, missingness, ...). Dimensions without an evaluator yet are 'not_assessed' and cap the claim, never count as adequate."
+}

Changed2 schema fields changedv1.0.19Sep 18, 2026

addedOutput schema / properties / sample_confidence
```
Added value: +{
+  "type": "string"
+}
```

changedOutput schema / required

Previous value: -[
-  "metric_a",
-  "metric_b",
-  "lag_days",
-  "n"
-]New value: +[
+  "metric_a",
+  "metric_b",
+  "lag_days",
+  "n",
+  "sample_confidence"
+]

Changed2 schema fields changedSep 15, 2026

addedOutput schema / properties / evidence_a

Added value: +{
+  "anyOf": [
+    {
+      "description": "Coverage/quality of the data a single-metric analytical result is\nbased on. See evidence.build_evidence for how each field is computed.",
+      "properties": {
+        "confidence": {
+          "type": "string"
+        },
+        "coverage_ratio": {
+          "type": "number"
+        },
+        "expected_days": {
+          "type": "integer"
+        },
+        "freshness_days": {
+          "anyOf": [
+            {
+              "type": "integer"
+            },
+            {
+              "type": "null"
+            }
+          ],
+          "default": null
+        },
+        "gaps": {
+          "items": {
+            "properties": {
+              "days": {
+                "type": "integer"
+              },
+              "end": {
+                "type": "string"
+              },
+              "start": {
+                "type": "string"
+              }
+            },
+            "required": [
+              "start",
+              "end",
+              "days"
+            ],
+            "type": "object"
+          },
+          "type": "array"
+        },
+        "measurement_count": {
+          "type": "integer"
+        },
+        "missing_days": {
+          "type": "integer"
+        },
+        "observed_days": {
+          "type": "integer"
+        },
+        "observed_end": {
+          "anyOf": [
+            {
+              "type": "string"
+            },
+            {
+              "type": "null"
+            }
+          ],
+          "default": null
+        },
+        "observed_start": {
+          "anyOf": [
+            {
+              "type": "string"
+            },
+            {
+              "type": "null"
+            }
+          ],
+          "default": null
+        },
+        "recent_gap_days": {
+          "type": "integer"
+        },
+        "requested_end": {
+          "type": "string"
+        },
+        "requested_start": {
+          "type": "string"
+        }
+      },
+      "required": [
+        "requested_start",
+        "requested_end",
+        "expected_days",
+        "observed_days",
+        "coverage_ratio",
+        "missing_days",
+        "measurement_count",
+        "gaps",
+        "recent_gap_days",
+        "confidence"
+      ],
+      "type": "object"
+    },
+    {
+      "type": "null"
+    }
+  ],
+  "default": null
+}

addedOutput schema / properties / evidence_b

Added value: +{
+  "anyOf": [
+    {
+      "description": "Coverage/quality of the data a single-metric analytical result is\nbased on. See evidence.build_evidence for how each field is computed.",
+      "properties": {
+        "confidence": {
+          "type": "string"
+        },
+        "coverage_ratio": {
+          "type": "number"
+        },
+        "expected_days": {
+          "type": "integer"
+        },
+        "freshness_days": {
+          "anyOf": [
+            {
+              "type": "integer"
+            },
+            {
+              "type": "null"
+            }
+          ],
+          "default": null
+        },
+        "gaps": {
+          "items": {
+            "properties": {
+              "days": {
+                "type": "integer"
+              },
+              "end": {
+                "type": "string"
+              },
+              "start": {
+                "type": "string"
+              }
+            },
+            "required": [
+              "start",
+              "end",
+              "days"
+            ],
+            "type": "object"
+          },
+          "type": "array"
+        },
+        "measurement_count": {
+          "type": "integer"
+        },
+        "missing_days": {
+          "type": "integer"
+        },
+        "observed_days": {
+          "type": "integer"
+        },
+        "observed_end": {
+          "anyOf": [
+            {
+              "type": "string"
+            },
+            {
+              "type": "null"
+            }
+          ],
+          "default": null
+        },
+        "observed_start": {
+          "anyOf": [
+            {
+              "type": "string"
+            },
+            {
+              "type": "null"
+            }
+          ],
+          "default": null
+        },
+        "recent_gap_days": {
+          "type": "integer"
+        },
+        "requested_end": {
+          "type": "string"
+        },
+        "requested_start": {
+          "type": "string"
+        }
+      },
+      "required": [
+        "requested_start",
+        "requested_end",
+        "expected_days",
+        "observed_days",
+        "coverage_ratio",
+        "missing_days",
+        "measurement_count",
+        "gaps",
+        "recent_gap_days",
+        "confidence"
+      ],
+      "type": "object"
+    },
+    {
+      "type": "null"
+    }
+  ],
+  "default": null
+}

Addedv1.0.16Sep 15, 2026
Removedv1.0.15Sep 15, 2026
Addedv1.0.11Sep 13, 2026

TDQS

A4.5/5.0

Behavior5/5

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

Annotations already cover the safety profile (read-only, idempotent, non-destructive), and the description adds genuinely non-obvious context: the local SQLite file vs. cloud-model egress caveat, and the correlation-vs-causation interpretation warning. These are behavioral traits no structured field conveys.

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-loaded with the operation, then cleanly partitioned into use / do-not-use / privacy blocks. Slightly lengthy because of the multi-sentence privacy paragraph, but every block carries actionable information and there is no filler.

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?

With an output schema present, return values need no explanation, and the alternatives, interpretation caveat, and privacy implications are all covered. The one remaining gap is the metric identifier format for the two required parameters, which an agent must guess.

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 60%: lag_days and the date bounds are well documented in the schema itself. However, metric_a and metric_b carry no schema description, and the description does not explain the expected metric identifier format or how invalid/unknown metric names are handled, so it only partially compensates for the gap.

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 operation (Pearson correlation), the resources (two metrics), and the join semantics (same window, joined by date). It also explicitly disambiguates from siblings get_baseline, calculate_metric_trend, and detect_metric_anomalies, so an agent can route 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?

Provides explicit when-to-use criteria (two different named or implied metrics moving together) and explicit when-not-to-use criteria (single-metric questions) with named replacement tools. This is the strongest form of routing guidance.

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

Find correlation between two metrics

Instructions

Input Schema

Output Schema

Schema Changelog

TDQS

Other Tools