Previous value: -"NER label to prefer for `q` (boost, not a filter). Supply when you can categorize the term (company→ORG, place→GPE, person→PERSON, ...). Describes the ENTITY only — it is not applied to `metric`."New value: +"NER label to prefer for `q` — a boost, not a filter. Set it when you can categorize the term: company → ORG, place → GPE, person → PERSON. It never applies to `metric`."

Added value: +{
+  "description": "How many candidates to resolve for each of `q` and `metric`. Raising it widens what the tool considers, not just what it shows: a deeper metric can become the one `next_call` names.",
+  "maximum": 20,
+  "minimum": 1,
+  "type": "integer"
+}

Previous value: -"The measure you want, when you already know it — e.g. \"gross margin\", \"passenger cruise days\", \"capex\". Supplying it is the FAST path: the tool resolves the entity+metric pair directly and hands back a runnable next_call, instead of listing every metric the entity has. Omit it only to browse what exists."New value: +"The measure, when you already know it — \"gross margin\", \"capex\". Supplying it resolves the entity+metric pair directly; omit it to browse everything the entity has."

Previous value: -"The NAME of the entity (or metric) to look up, min 2 chars — e.g. \"Carnival\", \"United States\", \"Nvidia\". Put the measure in `metric`, not here."New value: +"The entity or metric to look up by name — \"Carnival\", \"United States\", \"Nvidia\". Put the measure in `metric`, not here."

Previous value: -"Narrow resolution to a \"thing\" (\"entity\") or a \"measure\" (\"metric\"). Omit to search both."New value: +"Narrow resolution to one kind, an entity or a metric. Omit to resolve both."

Added value: +{
+  "description": "The other nodes `q` resolved to, best first.",
+  "items": {
+    "additionalProperties": {},
+    "properties": {
+      "coverage": {
+        "additionalProperties": {},
+        "properties": {
+          "total": {
+            "type": "number"
+          },
+          "total_capped": {
+            "description": "`total` is a floor.",
+            "type": "boolean"
+          }
+        },
+        "required": [
+          "total",
+          "total_capped"
+        ],
+        "type": "object"
+      },
+      "id": {
+        "type": "string"
+      },
+      "kind": {
+        "type": "string"
+      },
+      "name": {
+        "description": "Canonical graph name — search on this.",
+        "type": "string"
+      },
+      "type": {
+        "description": "entity or metric; also what `coverage` counts.",
+        "type": "string"
+      }
+    },
+    "required": [
+      "id",
+      "name",
+      "type"
+    ],
+    "type": "object"
+  },
+  "type": "array"
+}

Previous value: -[
-  {
-    "additionalProperties": false,
-    "properties": {
-      "name": {
-        "type": "string"
-      },
-      "node_id": {
-        "type": "string"
-      },
-      "type": {
-        "type": "string"
-      }
-    },
-    "required": [
-      "node_id",
-      "name",
-      "type"
-    ],
-    "type": "object"
-  },
-  {
-    "type": "null"
-  }
-]New value: +[
+  {
+    "additionalProperties": false,
+    "properties": {
+      "id": {
+        "type": "string"
+      },
+      "name": {
+        "type": "string"
+      }
+    },
+    "required": [
+      "id",
+      "name"
+    ],
+    "type": "object"
+  },
+  {
+    "type": "null"
+  }
+]

Added value: +"Lookup path: the resolved entity."

Removed value: -{
-  "items": {
-    "additionalProperties": false,
-    "properties": {
-      "name": {
-        "type": "string"
-      },
-      "node_id": {
-        "type": "string"
-      },
-      "type": {
-        "type": "string"
-      }
-    },
-    "required": [
-      "node_id",
-      "name",
-      "type"
-    ],
-    "type": "object"
-  },
-  "type": "array"
-}

Added value: +{
+  "description": "Runners-up.",
+  "items": {
+    "additionalProperties": false,
+    "properties": {
+      "id": {
+        "type": "string"
+      },
+      "name": {
+        "type": "string"
+      }
+    },
+    "required": [
+      "id",
+      "name"
+    ],
+    "type": "object"
+  },
+  "type": "array"
+}

Previous value: -"The OUTCOME. Discovery path (no `metric`): at least one match has live data coverage, not mere node resolution. Lookup path (`metric` supplied): both halves resolved and the pinned metric passed the name test — read `verified` for what was actually CHECKED. Never means a chart exists; only running `next_call` establishes that."New value: +"Whether Tako holds matching data; `verified` says on what evidence."

Added value: +{
+  "description": "The verdict, and the one next action.",
+  "type": "string"
+}

Previous value: -"The resolved matches and their coverage, each entry carrying the node id to pin. To fetch a specific metric precisely: call tako_search or tako_answer with node_ids=[<the metric's node_id>] AND strict:true — an entity-only pin without strict does not steer retrieval."New value: +"The nodes whose coverage was drilled, best first."

Added value: +{
+  "items": {
+    "type": "string"
+  },
+  "type": "array"
+}

Added value: +"Headline-first."

Added value: +{
+  "description": "Graph node id.",
+  "type": "string"
+}

Added value: +"Canonical graph name."

Removed value: -{
-  "description": "Pin this in a follow-up's node_ids WITH strict:true.",
-  "type": "string"
-}

Previous value: -[
-  "name",
-  "node_id"
-]New value: +[
+  "name",
+  "id"
+]

Removed value: -{
-  "description": "More coverage entries exist than are listed here — the full NAME list is in the text channel.",
-  "type": "boolean"
-}

Removed value: -{
-  "type": "string"
-}

Added value: +"Entries in all, not entries listed."

Added value: +{
+  "description": "`total` is a floor.",
+  "type": "boolean"
+}

Added value: +"More entries exist than are listed."

Previous value: -[
-  "kind",
-  "total",
-  "truncated",
-  "items"
-]New value: +[
+  "total",
+  "total_capped"
+]

Added value: +{
+  "description": "The `metric` phrase that narrowed this list. When set, `total` counts only matching entries.",
+  "type": "string"
+}

Added value: +{
+  "type": "string"
+}

Added value: +{
+  "type": "string"
+}

Added value: +"Canonical graph name — search on this."

Removed value: -{
-  "type": "string"
-}

Added value: +"entity or metric; also what `coverage` counts."

Previous value: -[
-  "node_id",
-  "name",
-  "type",
-  "coverage"
-]New value: +[
+  "id",
+  "name",
+  "type",
+  "coverage"
+]

Previous value: -[
-  {
-    "additionalProperties": false,
-    "properties": {
-      "name": {
-        "type": "string"
-      },
-      "node_id": {
-        "type": "string"
-      },
-      "type": {
-        "type": "string"
-      }
-    },
-    "required": [
-      "node_id",
-      "name",
-      "type"
-    ],
-    "type": "object"
-  },
-  {
-    "type": "null"
-  }
-]New value: +[
+  {
+    "additionalProperties": false,
+    "properties": {
+      "id": {
+        "type": "string"
+      },
+      "name": {
+        "type": "string"
+      }
+    },
+    "required": [
+      "id",
+      "name"
+    ],
+    "type": "object"
+  },
+  {
+    "type": "null"
+  }
+]

Previous value: -"The metric whose node_id belongs in the follow-up's node_ids."New value: +"Lookup path: the resolved metric."

Removed value: -{
-  "description": "Runners-up. The top metric is right ~80% of the time and the top three ~93-95%, so check these before accepting the primary.",
-  "items": {
-    "additionalProperties": false,
-    "properties": {
-      "name": {
-        "type": "string"
-      },
-      "node_id": {
-        "type": "string"
-      },
-      "type": {
-        "type": "string"
-      }
-    },
-    "required": [
-      "node_id",
-      "name",
-      "type"
-    ],
-    "type": "object"
-  },
-  "type": "array"
-}

Added value: +{
+  "description": "Runners-up.",
+  "items": {
+    "additionalProperties": false,
+    "properties": {
+      "id": {
+        "type": "string"
+      },
+      "name": {
+        "type": "string"
+      }
+    },
+    "required": [
+      "id",
+      "name"
+    ],
+    "type": "object"
+  },
+  "type": "array"
+}

Removed value: -{
-  "type": "string"
-}

Previous value: -[
-  {
-    "additionalProperties": false,
-    "properties": {
-      "node_ids": {
-        "items": {
-          "type": "string"
-        },
-        "type": "array"
-      },
-      "query": {
-        "type": "string"
-      },
-      "strict": {
-        "type": "boolean"
-      },
-      "tool": {
-        "enum": [
-          "tako_search",
-          "tako_answer"
-        ],
-        "type": "string"
-      }
-    },
-    "required": [
-      "tool",
-      "query",
-      "node_ids",
-      "strict"
-    ],
-    "type": "object"
-  },
-  {
-    "type": "null"
-  }
-]New value: +[
+  {
+    "additionalProperties": false,
+    "properties": {
+      "query": {
+        "type": "string"
+      },
+      "tool": {
+        "type": "string"
+      }
+    },
+    "required": [
+      "tool",
+      "query"
+    ],
+    "type": "object"
+  },
+  {
+    "type": "null"
+  }
+]

Previous value: -"Ready-to-run follow-up: call this tool with exactly this query, node_ids and strict. node_ids holds the METRIC node only — strict is an OR over pinned nodes, so adding the entity id widens the filter back out. Null when no metric resolved."New value: +"A follow-up search in canonical names. Null when no target is unambiguous."

Removed value: -{
-  "type": "string"
-}

Previous value: -"WHAT WAS CHECKED, as distinct from `found`, which is the outcome. `coverage`: a coverage list was drilled. `pair`: the metric is on the entity's own metric list — the strongest free evidence there is. `unlinked`: the entity's list was checked and holds nothing matching, so a pinned call will probably return 0 cards; the emitted next_call therefore drops the pin. `resolution`: no pair evidence (check skipped or failed) — treat exactly as before."New value: +"What was checked. `pair`: the metric is on the entity's own list. `coverage`: a list was drilled. `unlinked`: the list was checked, the metric is absent. `resolution`: names resolved only."

Previous value: -[
-  "found",
-  "query",
-  "matches",
-  "next_call"
-]New value: +[
+  "found",
+  "matches",
+  "candidates",
+  "next_call"
+]

Previous value: -"True when at least one match has live data coverage — not mere node resolution."New value: +"The OUTCOME. Discovery path (no `metric`): at least one match has live data coverage, not mere node resolution. Lookup path (`metric` supplied): both halves resolved and the pinned metric passed the name test — read `verified` for what was actually CHECKED. Never means a chart exists; only running `next_call` establishes that."

Added value: +{
+  "description": "WHAT WAS CHECKED, as distinct from `found`, which is the outcome. `coverage`: a coverage list was drilled. `pair`: the metric is on the entity's own metric list — the strongest free evidence there is. `unlinked`: the entity's list was checked and holds nothing matching, so a pinned call will probably return 0 cards; the emitted next_call therefore drops the pin. `resolution`: no pair evidence (check skipped or failed) — treat exactly as before.",
+  "enum": [
+    "coverage",
+    "pair",
+    "unlinked",
+    "resolution"
+  ],
+  "type": "string"
+}

Previous value: -"NER label to prefer (boost, not a filter). Supply when you can categorize the term (company→ORG, place→GPE, person→PERSON, ...)."New value: +"NER label to prefer for `q` (boost, not a filter). Supply when you can categorize the term (company→ORG, place→GPE, person→PERSON, ...). Describes the ENTITY only — it is not applied to `metric`."

Added value: +{
+  "description": "The measure you want, when you already know it — e.g. \"gross margin\", \"passenger cruise days\", \"capex\". Supplying it is the FAST path: the tool resolves the entity+metric pair directly and hands back a runnable next_call, instead of listing every metric the entity has. Omit it only to browse what exists.",
+  "minLength": 2,
+  "type": "string"
+}

Previous value: -"The NAME of one entity or one metric to look up (min 2 chars). Not a full question: for \"Carnival passenger cruise days\" pass \"Carnival\" and read the metric off the returned coverage.names."New value: +"The NAME of the entity (or metric) to look up, min 2 chars — e.g. \"Carnival\", \"United States\", \"Nvidia\". Put the measure in `metric`, not here."

Added value: +{
+  "anyOf": [
+    {
+      "additionalProperties": false,
+      "properties": {
+        "name": {
+          "type": "string"
+        },
+        "node_id": {
+          "type": "string"
+        },
+        "type": {
+          "type": "string"
+        }
+      },
+      "required": [
+        "node_id",
+        "name",
+        "type"
+      ],
+      "type": "object"
+    },
+    {
+      "type": "null"
+    }
+  ]
+}

Added value: +{
+  "items": {
+    "additionalProperties": false,
+    "properties": {
+      "name": {
+        "type": "string"
+      },
+      "node_id": {
+        "type": "string"
+      },
+      "type": {
+        "type": "string"
+      }
+    },
+    "required": [
+      "node_id",
+      "name",
+      "type"
+    ],
+    "type": "object"
+  },
+  "type": "array"
+}

Added value: +{
+  "description": "The resolved matches and their coverage, each entry carrying the node id to pin. To fetch a specific metric precisely: call tako_search or tako_answer with node_ids=[<the metric's node_id>] AND strict:true — an entity-only pin without strict does not steer retrieval.",
+  "items": {
+    "additionalProperties": {},
+    "properties": {
+      "coverage": {
+        "additionalProperties": {},
+        "properties": {
+          "items": {
+            "items": {
+              "additionalProperties": false,
+              "properties": {
+                "name": {
+                  "type": "string"
+                },
+                "node_id": {
+                  "description": "Pin this in a follow-up's node_ids WITH strict:true.",
+                  "type": "string"
+                }
+              },
+              "required": [
+                "name",
+                "node_id"
+              ],
+              "type": "object"
+            },
+            "type": "array"
+          },
+          "items_truncated": {
+            "description": "More coverage entries exist than are listed here — the full NAME list is in the text channel.",
+            "type": "boolean"
+          },
+          "kind": {
+            "type": "string"
+          },
+          "total": {
+            "type": "number"
+          },
+          "truncated": {
+            "type": "boolean"
+          }
+        },
+        "required": [
+          "kind",
+          "total",
+          "truncated",
+          "items"
+        ],
+        "type": "object"
+      },
+      "name": {
+        "type": "string"
+      },
+      "node_id": {
+        "type": "string"
+      },
+      "type": {
+        "type": "string"
+      },
+      "unavailable": {
+        "type": "boolean"
+      }
+    },
+    "required": [
+      "node_id",
+      "name",
+      "type",
+      "coverage"
+    ],
+    "type": "object"
+  },
+  "type": "array"
+}

Added value: +{
+  "anyOf": [
+    {
+      "additionalProperties": false,
+      "properties": {
+        "name": {
+          "type": "string"
+        },
+        "node_id": {
+          "type": "string"
+        },
+        "type": {
+          "type": "string"
+        }
+      },
+      "required": [
+        "node_id",
+        "name",
+        "type"
+      ],
+      "type": "object"
+    },
+    {
+      "type": "null"
+    }
+  ],
+  "description": "The metric whose node_id belongs in the follow-up's node_ids."
+}

Added value: +{
+  "description": "Runners-up. The top metric is right ~80% of the time and the top three ~93-95%, so check these before accepting the primary.",
+  "items": {
+    "additionalProperties": false,
+    "properties": {
+      "name": {
+        "type": "string"
+      },
+      "node_id": {
+        "type": "string"
+      },
+      "type": {
+        "type": "string"
+      }
+    },
+    "required": [
+      "node_id",
+      "name",
+      "type"
+    ],
+    "type": "object"
+  },
+  "type": "array"
+}

Added value: +{
+  "type": "string"
+}

Previous value: -[
-  {
-    "additionalProperties": false,
-    "properties": {
-      "node_ids": {
-        "items": {
-          "type": "string"
-        },
-        "type": "array"
-      },
-      "query": {
-        "type": "string"
-      },
-      "tool": {
-        "const": "tako_search",
-        "type": "string"
-      }
-    },
-    "required": [
-      "tool",
-      "query",
-      "node_ids"
-    ],
-    "type": "object"
-  },
-  {
-    "type": "null"
-  }
-]New value: +[
+  {
+    "additionalProperties": false,
+    "properties": {
+      "node_ids": {
+        "items": {
+          "type": "string"
+        },
+        "type": "array"
+      },
+      "query": {
+        "type": "string"
+      },
+      "strict": {
+        "type": "boolean"
+      },
+      "tool": {
+        "enum": [
+          "tako_search",
+          "tako_answer"
+        ],
+        "type": "string"
+      }
+    },
+    "required": [
+      "tool",
+      "query",
+      "node_ids",
+      "strict"
+    ],
+    "type": "object"
+  },
+  {
+    "type": "null"
+  }
+]

Previous value: -"Ready-to-run follow-up when coverage was found: call tako_search with exactly this query and node_ids pinned. Null when no match has coverage."New value: +"Ready-to-run follow-up: call this tool with exactly this query, node_ids and strict. node_ids holds the METRIC node only — strict is an OR over pinned nodes, so adding the entity id widens the filter back out. Null when no metric resolved."

Previous value: -[
-  "found",
-  "query",
-  "next_call"
-]New value: +[
+  "found",
+  "query",
+  "matches",
+  "next_call"
+]

Removed value: -{
-  "description": "Hunting one specific metric? Case-insensitive filter matching WORDS in the coverage names + aliases, applied server-side across the FULL coverage (e.g. q=\"Capital One\", coverage_filter=\"charges-off\"). Use whole words as they appear in the name — a partial word (\"charge\" for \"charges\") may not match. Use when the unfiltered list came back truncated without the metric you expected; omit for the general coverage overview.",
-  "minLength": 1,
-  "type": "string"
-}

Previous value: -"The NAME of one entity or one metric to look up (min 2 chars). Not a full question: if your lookup names both a thing and a measure (\"Carnival passenger cruise days\"), put the entity here (\"Carnival\") and the metric words in coverage_filter (\"passenger cruise days\")."New value: +"The NAME of one entity or one metric to look up (min 2 chars). Not a full question: for \"Carnival passenger cruise days\" pass \"Carnival\" and read the metric off the returned coverage.names."

Added value: +{
+  "description": "Hunting one specific metric? Case-insensitive filter matching WORDS in the coverage names + aliases, applied server-side across the FULL coverage (e.g. q=\"Capital One\", coverage_filter=\"charges-off\"). Use whole words as they appear in the name — a partial word (\"charge\" for \"charges\") may not match. Use when the unfiltered list came back truncated without the metric you expected; omit for the general coverage overview.",
+  "minLength": 1,
+  "type": "string"
+}

Previous value: -"Entity or metric name to look up (min 2 chars)."New value: +"The NAME of one entity or one metric to look up (min 2 chars). Not a full question: if your lookup names both a thing and a measure (\"Carnival passenger cruise days\"), put the entity here (\"Carnival\") and the metric words in coverage_filter (\"passenger cruise days\")."

Previous value: -"True when at least one match has live data coverage — not mere node resolution. A resolved node with no coverage (or whose coverage lookup failed) yields false."New value: +"True when at least one match has live data coverage — not mere node resolution."

Removed value: -{
-  "items": {
-    "additionalProperties": false,
-    "properties": {
-      "coverage": {
-        "additionalProperties": false,
-        "properties": {
-          "capped": {
-            "type": "boolean"
-          },
-          "kind": {
-            "enum": [
-              "metrics",
-              "entities"
-            ],
-            "type": "string"
-          },
-          "names": {
-            "items": {
-              "type": "string"
-            },
-            "type": "array"
-          },
-          "total": {
-            "maximum": 9007199254740991,
-            "minimum": -9007199254740991,
-            "type": "integer"
-          },
-          "truncated": {
-            "type": "boolean"
-          }
-        },
-        "required": [
-          "kind",
-          "names",
-          "total",
-          "truncated",
-          "capped"
-        ],
-        "type": "object"
-      },
-      "label": {
-        "anyOf": [
-          {
-            "type": "string"
-          },
-          {
-            "type": "null"
-          }
-        ]
-      },
-      "name": {
-        "type": "string"
-      },
-      "node_id": {
-        "type": "string"
-      },
-      "type": {
-        "type": "string"
-      },
-      "unavailable": {
-        "type": "boolean"
-      }
-    },
-    "required": [
-      "node_id",
-      "name",
-      "type",
-      "coverage"
-    ],
-    "type": "object"
-  },
-  "type": "array"
-}

Added value: +{
+  "anyOf": [
+    {
+      "additionalProperties": false,
+      "properties": {
+        "node_ids": {
+          "items": {
+            "type": "string"
+          },
+          "type": "array"
+        },
+        "query": {
+          "type": "string"
+        },
+        "tool": {
+          "const": "tako_search",
+          "type": "string"
+        }
+      },
+      "required": [
+        "tool",
+        "query",
+        "node_ids"
+      ],
+      "type": "object"
+    },
+    {
+      "type": "null"
+    }
+  ],
+  "description": "Ready-to-run follow-up when coverage was found: call tako_search with exactly this query and node_ids pinned. Null when no match has coverage."
+}

Removed value: -{
-  "items": {
-    "additionalProperties": false,
-    "properties": {
-      "name": {
-        "type": "string"
-      },
-      "type": {
-        "type": "string"
-      }
-    },
-    "required": [
-      "name",
-      "type"
-    ],
-    "type": "object"
-  },
-  "type": "array"
-}

Removed value: -{
-  "type": "string"
-}

Previous value: -[
-  "found",
-  "query",
-  "summary",
-  "matches",
-  "other_matches"
-]New value: +[
+  "found",
+  "query",
+  "next_call"
+]