imf-mcp-server

Added value: +{
+  "default": false,
+  "description": "Return only codes reported by the dataflow-wide availability constraint. Default false keeps ordinary codelist discovery unchanged.",
+  "type": "boolean"
+}

Added value: +{
+  "const": true,
+  "description": "True when dimensions contain published availability coverage rather than codelists.",
+  "type": "boolean"
+}

Previous value: -"A single dimension with its codelist."New value: +"A single dimension with its codelist or published availability coverage."

Added value: +{
+  "description": "Codes reported with published data before codelist_filter. Present when available_only is true.",
+  "type": "number"
+}

Previous value: -"Valid codes for this dimension. Unselected previews show up to 50 entries after optional filtering. Select dimension_id and use limit/offset for a bounded page of up to 200 entries. Empty means the filter matched nothing when codelist_filter is echoed back, and that the codelist could not be resolved when it is not — see notice."New value: +"Valid codelist codes for this dimension, or codes reported with published data when available_only is true. Unselected previews show up to 50 entries after optional filtering. Select dimension_id and use limit/offset for a bounded page of up to 200 entries. Empty means the filter matched nothing when codelist_filter is echoed back, no coverage was reported in availability mode, or the codelist could not be resolved in normal mode — see notice."

Previous value: -"Codes in the complete resolved codelist before codelist_filter is applied."New value: +"Source codes before codelist_filter: the complete resolved codelist normally, or published codes when available_only is true."

Previous value: -"Machine-readable failure mode. Declared by this tool: `dataflow_not_found`: dataflow_id does not match any known dataflow on api.imf.org `dimension_not_found`: dimension_id does not match a dimension in the selected dataflow `structure_unavailable`: api.imf.org returns non-200 on the DSD endpoint `dataflow_list_unavailable`: The dataflow catalog that dataflow_id is resolved against could not be fetched — fires before the DSD lookup is attempted Other values are possible when a failure originates below the handler."New value: +"Machine-readable failure mode. Declared by this tool: `dataflow_not_found`: dataflow_id does not match any known dataflow on api.imf.org `dimension_not_found`: dimension_id does not match a dimension in the selected dataflow `structure_unavailable`: api.imf.org returns non-200 on the DSD endpoint `dataflow_list_unavailable`: The dataflow catalog that dataflow_id is resolved against could not be fetched — fires before the DSD lookup is attempted `availability_unavailable`: available_only is true and the dataflow-wide availability constraint cannot be fetched or parsed Other values are possible when a failure originates below the handler."

Previous value: -[
-  "dataflow_not_found",
-  "dimension_not_found",
-  "structure_unavailable",
-  "dataflow_list_unavailable"
-]New value: +[
+  "dataflow_not_found",
+  "dimension_not_found",
+  "structure_unavailable",
+  "dataflow_list_unavailable",
+  "availability_unavailable"
+]

Added value: +{
+  "description": "Total series published by the dataflow. Present when available_only is true.",
+  "type": "number"
+}

Added value: +{
+  "anyOf": [
+    {
+      "type": "string"
+    },
+    {
+      "type": "null"
+    }
+  ],
+  "description": "Latest period with published data, or null when the constraint omits it."
+}

Added value: +{
+  "anyOf": [
+    {
+      "type": "string"
+    },
+    {
+      "type": "null"
+    }
+  ],
+  "description": "Earliest period with published data, or null when the constraint omits it."
+}

Added value: +1

Previous value: -"Machine-readable failure mode. Declared by this tool: `canvas_not_found`: canvas_id does not match any registered DataCanvas session (expired, wrong session, or canvas disabled) `missing_table`: The canvas exists but sql references a table that is not staged on it — the table expired, was dropped, or the name is wrong `invalid_sql`: sql is not a single SELECT statement (a leading WITH … SELECT counts as one), or it is SELECT-shaped but fails to prepare — unknown column, unknown function, or a syntax error `sql_not_permitted`: sql parses as a SELECT but the read-only gate refuses it — it calls an external-data or PRAGMA table function, reads a system catalog, or plans an operator outside the read-only allowlist Other values are possible when a failure originates below the handler."New value: +"Machine-readable failure mode. Declared by this tool: `canvas_not_found`: canvas_id does not match any registered DataCanvas session (expired, wrong session, or canvas disabled) `missing_table`: The canvas exists but sql references a table that is not staged on it — the table expired, was dropped, or the name is wrong `invalid_sql`: sql is not a single SELECT statement (a leading WITH … SELECT counts as one), or it is SELECT-shaped but fails to prepare — unknown column, unknown function, or a syntax error `sql_not_permitted`: sql parses as a SELECT but the read-only gate refuses it — it calls an external-data or PRAGMA table function, reads a system catalog, or plans an operator outside the read-only allowlist `response_too_large`: The first result row cannot fit in the complete structured and formatted response budget Other values are possible when a failure originates below the handler."

Previous value: -[
-  "canvas_not_found",
-  "missing_table",
-  "invalid_sql",
-  "sql_not_permitted"
-]New value: +[
+  "canvas_not_found",
+  "missing_table",
+  "invalid_sql",
+  "sql_not_permitted",
+  "response_too_large"
+]

Previous value: -"Number of rows materialized in rows. Equals the canvas row limit when truncated is true — DataCanvas does not report a pre-cap total, so this is never larger than rows.length."New value: +"Number of materialized rows returned in rows. Always equals rows.length and never claims a pre-cap total."

Previous value: -"Query result rows, capped at the canvas row limit (default 10,000)."New value: +"Largest result-row prefix whose complete structured and formatted response fits the 100,000-character response budget, after the canvas row limit (default 10,000) is applied."

Previous value: -"True when the query matched more rows than the canvas row limit and the result was capped. Page the remainder with a stable ORDER BY plus LIMIT/OFFSET, or narrow the query with WHERE or aggregation."New value: +"True when DataCanvas capped the query at its row limit or the server omitted materialized rows to fit the response-size budget. Page the remainder with a stable ORDER BY plus LIMIT/OFFSET, or narrow the query with WHERE or aggregation."

Previous value: -"Canvas ID returned by imf_query_dataset when results were too large for inline delivery."New value: +"Canvas ID returned by imf_query_dataset whenever staged=true, from automatic spillover or output_mode=\"canvas\"."

Previous value: -"Canvas ID returned by imf_query_dataset when results were too large for inline delivery."New value: +"Canvas ID returned by imf_query_dataset whenever staged=true. Call imf_dataframe_describe with it before writing SQL."

Previous value: -"Existing canvas ID to accumulate results into across multiple queries. Omit to allocate a fresh canvas; the response includes a canvas_id when results spill to DataCanvas."New value: +"Existing canvas ID to accumulate results into across multiple queries. This selects the destination only; it does not force staging. Use output_mode=\"canvas\" to stage an under-budget result."

Added value: +{
+  "default": "auto",
+  "description": "Result placement. auto returns an under-budget result inline and spills only when needed. canvas explicitly stages the full result, using canvas_id when supplied or allocating a fresh canvas.",
+  "enum": [
+    "auto",
+    "canvas"
+  ],
+  "type": "string"
+}

Previous value: -"Start of time range (inclusive). Accepts any of YYYY (annual), YYYY-SN (semi-annual, e.g. 2023-S1), YYYY-QN (quarterly, e.g. 2023-Q1), YYYY-MM (monthly), or YYYY-MM-DD (daily), whatever the dataflow's frequency. The bound covers the whole period it names, so start_period 2023 admits 2023-M01 and 2023-Q1. Observations before this period are excluded from the result."New value: +"Start of time range (inclusive). Accepts any of YYYY (annual), YYYY-SN (semi-annual, e.g. 2023-S1), YYYY-QN (quarterly, e.g. 2023-Q1), YYYY-MM (monthly), or a calendar-valid YYYY-MM-DD (daily), whatever the dataflow's frequency. The bound covers the whole period it names, so start_period 2023 admits 2023-M01 and 2023-Q1. Observations before this period are excluded from the result."

Previous value: -[
-  {
-    "not": {
-      "required": [
-        "error"
-      ]
-    },
-    "required": [
-      "dataflow_id",
-      "key",
-      "observations",
-      "series_attributes",
-      "observation_count",
-      "truncated",
-      "source"
-    ]
-  },
-  {
-    "required": [
-      "error"
-    ]
-  }
-]New value: +[
+  {
+    "not": {
+      "required": [
+        "error"
+      ]
+    },
+    "required": [
+      "dataflow_id",
+      "key",
+      "observations",
+      "series_attributes",
+      "observation_count",
+      "staged",
+      "truncated",
+      "source"
+    ]
+  },
+  {
+    "required": [
+      "error"
+    ]
+  }
+]

Previous value: -"DataCanvas session ID — present when truncated=true. Pass to imf_dataframe_query or imf_dataframe_describe to query the full result."New value: +"DataCanvas session ID — present when staged=true. Pass first to imf_dataframe_describe, then to imf_dataframe_query."

Previous value: -"Machine-readable failure mode. Declared by this tool: `dataflow_not_found`: dataflow_id does not match any known dataflow on api.imf.org `no_data`: Key is structurally valid but the dataflow holds no series for this code combination, or the dataflow publishes no series at all `no_data_in_range`: The key returned observations but start_period/end_period excluded every one of them `key_dimension_mismatch`: Number of dot-separated segments in key does not match the dataflow's DSD dimension count `empty_key_segment`: A dot-separated position in key is empty or blank, which matches no series upstream `invalid_period_format`: start_period or end_period is not one of the recognized period formats `invalid_period_range`: start_period is later than end_period `structure_unavailable`: api.imf.org returns non-200 on the data endpoint `dataflow_list_unavailable`: The dataflow catalog that dataflow_id is resolved against could not be fetched — fires before the DSD and data lookups are attempted Other values are possible when a failure originates below the handler."New value: +"Machine-readable failure mode. Declared by this tool: `dataflow_not_found`: dataflow_id does not match any known dataflow on api.imf.org `no_data`: Key is structurally valid but the dataflow holds no series for this code combination, or the dataflow publishes no series at all `no_data_in_range`: The key returned observations but start_period/end_period excluded every one of them `key_dimension_mismatch`: Number of dot-separated segments in key does not match the dataflow's DSD dimension count `empty_key_segment`: A dot-separated position in key is empty or blank, which matches no series upstream `invalid_period_format`: start_period or end_period is not one of the recognized period formats `invalid_period_range`: start_period is later than end_period `structure_unavailable`: The dataflow structure (DSD) cannot be fetched after the dataflow catalog resolved successfully `canvas_unavailable`: output_mode=\"canvas\" was requested but DataCanvas is disabled `response_too_large`: Fixed staged-result metadata exceeds the response budget before any observation preview can be included `dataflow_list_unavailable`: The dataflow catalog that dataflow_id is resolved against could not be fetched — fires before the DSD and data lookups are attempted Other values are possible when a failure originates below the handler."

Previous value: -[
-  "dataflow_not_found",
-  "no_data",
-  "no_data_in_range",
-  "key_dimension_mismatch",
-  "empty_key_segment",
-  "invalid_period_format",
-  "invalid_period_range",
-  "structure_unavailable",
-  "dataflow_list_unavailable"
-]New value: +[
+  "dataflow_not_found",
+  "no_data",
+  "no_data_in_range",
+  "key_dimension_mismatch",
+  "empty_key_segment",
+  "invalid_period_format",
+  "invalid_period_range",
+  "structure_unavailable",
+  "canvas_unavailable",
+  "response_too_large",
+  "dataflow_list_unavailable"
+]

Previous value: -"Populated when a period bound was set but some observations carry a time_period label the range filter does not recognize — those rows are returned unfiltered, so the requested range did not apply to them."New value: +"Populated when a period bound was set but some observations carry a time_period label the range filter does not recognize. Composes with staged retrieval_guidance when both apply."

Previous value: -"Inline observations. Empty when results spilled to canvas (see canvas_id / table_name)."New value: +"Inline observation preview. For staged results this may contain the full set or a budget-limited prefix; observation_count remains the full count."

Added value: +{
+  "description": "Present on every staged result. Identifies the imf_dataframe_describe-before-imf_dataframe_query retrieval workflow.",
+  "type": "string"
+}

Added value: +{
+  "description": "True when the complete observation set is stored on DataCanvas. canvas_id and table_name are present whenever true.",
+  "type": "boolean"
+}

Previous value: -"DuckDB table name on the canvas — present when truncated=true; reference in SQL via FROM <table_name>."New value: +"DuckDB table name on the canvas — present when staged=true; reference in SQL via FROM <table_name>."

Previous value: -"True when the result exceeded the inline limit and was staged on a DataCanvas table; canvas_id and table_name are populated and imf_dataframe_query provides SQL access to the full set."New value: +"True only when observations is an incomplete preview of observation_count. A result can be staged=true and truncated=false when every observation also fits inline."

Previous value: -"Optional case-insensitive substring to search within each dimension's codelist (code ID and name). When set, returns all matching entries per dimension instead of the first-50 window — useful for large codelists like WEO INDICATOR (145 entries). Example: \"CPI\" or \"PCPIPCH\" surfaces consumer price index codes without hitting the 50-entry cap."New value: +"Optional case-insensitive substring to search within each dimension's codelist (code ID and name). Filtering runs before the 50-entry preview or selected-dimension page. Example: \"CPI\" or \"Constant prices\" surfaces matching WEO indicator codes."

Added value: +1

Added value: +{
+  "description": "Exact dimension ID from this tool, e.g. INDICATOR. Select one dimension to page beyond its preview.",
+  "minLength": 1,
+  "type": "string"
+}

Added value: +{
+  "description": "Entries to return from the selected dimension. Valid only with dimension_id; default 50, maximum 200.",
+  "maximum": 200,
+  "minimum": 1,
+  "type": "integer"
+}

Added value: +{
+  "description": "Matching entries to skip in the selected dimension before this page. Valid only with dimension_id; default 0.",
+  "maximum": 9007199254740991,
+  "minimum": 0,
+  "type": "integer"
+}

Previous value: -[
-  {
-    "not": {
-      "required": [
-        "error"
-      ]
-    },
-    "required": [
-      "dataflow_id",
-      "agency_id",
-      "version",
-      "name",
-      "key_format",
-      "dimensions",
-      "source"
-    ]
-  },
-  {
-    "required": [
-      "error"
-    ]
-  }
-]New value: +[
+  {
+    "not": {
+      "required": [
+        "error"
+      ]
+    },
+    "required": [
+      "dataflow_id",
+      "agency_id",
+      "version",
+      "name",
+      "key_format",
+      "truncated",
+      "dimensions",
+      "source"
+    ]
+  },
+  {
+    "required": [
+      "error"
+    ]
+  }
+]

Added value: +{
+  "description": "Selected dimension ID. Absent when previews for every dimension were returned.",
+  "type": "string"
+}

Previous value: -"All dimensions of this dataflow with their codelists."New value: +"All dimension previews, or the one selected dimension page."

Previous value: -"Valid codes for this dimension. Up to 50 entries shown when no codelist_filter is set; use codelist_filter to search large codelists or the imf://database resource for the full list. Empty means the filter matched nothing when codelist_filter is echoed back, and that the codelist could not be resolved when it is not — see notice."New value: +"Valid codes for this dimension. Unselected previews show up to 50 entries after optional filtering. Select dimension_id and use limit/offset for a bounded page of up to 200 entries. Empty means the filter matched nothing when codelist_filter is echoed back, and that the codelist could not be resolved when it is not — see notice."

Previous value: -"True when the codelist has more than 50 entries and was truncated."New value: +"True when matching codes were omitted before or after this page."

Added value: +{
+  "description": "Codes matching codelist_filter before limit and offset are applied.",
+  "type": "number"
+}

Added value: +{
+  "description": "Offset for the next page when later matching codes remain.",
+  "type": "number"
+}

Added value: +{
+  "description": "Matching codes skipped before this dimension page.",
+  "type": "number"
+}

Added value: +{
+  "description": "Codes returned in this dimension page.",
+  "type": "number"
+}

Added value: +{
+  "description": "Codes in the complete resolved codelist before codelist_filter is applied.",
+  "type": "number"
+}

Previous value: -[
-  "id",
-  "name",
-  "position",
-  "codelist",
-  "codelist_truncated"
-]New value: +[
+  "id",
+  "name",
+  "position",
+  "codelist",
+  "codelist_truncated",
+  "unfiltered_count",
+  "matched_count",
+  "returned_count",
+  "offset"
+]

Previous value: -"Machine-readable failure mode. Declared by this tool: `dataflow_not_found`: dataflow_id does not match any known dataflow on api.imf.org `structure_unavailable`: api.imf.org returns non-200 on the DSD endpoint `dataflow_list_unavailable`: The dataflow catalog that dataflow_id is resolved against could not be fetched — fires before the DSD lookup is attempted Other values are possible when a failure originates below the handler."New value: +"Machine-readable failure mode. Declared by this tool: `dataflow_not_found`: dataflow_id does not match any known dataflow on api.imf.org `dimension_not_found`: dimension_id does not match a dimension in the selected dataflow `structure_unavailable`: api.imf.org returns non-200 on the DSD endpoint `dataflow_list_unavailable`: The dataflow catalog that dataflow_id is resolved against could not be fetched — fires before the DSD lookup is attempted Other values are possible when a failure originates below the handler."

Previous value: -[
-  "dataflow_not_found",
-  "structure_unavailable",
-  "dataflow_list_unavailable"
-]New value: +[
+  "dataflow_not_found",
+  "dimension_not_found",
+  "structure_unavailable",
+  "dataflow_list_unavailable"
+]

Previous value: -"Populated when a codelist_filter matched no entries anywhere, or when a dimension has no resolvable codelist — the two produce the same empty array and need opposite next steps."New value: +"Populated when a codelist_filter matched no entries anywhere, or when a dimension has no resolvable codelist, or when offset is past the final match."

Added value: +{
+  "description": "True when any returned dimension page omits matching codes.",
+  "type": "boolean"
+}

Previous value: -"http://json-schema.org/draft-07/schema#"New value: +"https://json-schema.org/draft/2020-12/schema"

Added value: +false

Previous value: -"http://json-schema.org/draft-07/schema#"New value: +"https://json-schema.org/draft/2020-12/schema"

Added value: +[
+  {
+    "not": {
+      "required": [
+        "error"
+      ]
+    },
+    "required": [
+      "canvas_id",
+      "tables",
+      "table_count"
+    ]
+  },
+  {
+    "required": [
+      "error"
+    ]
+  }
+]

Added value: +{
+  "additionalProperties": {},
+  "description": "Present when the call failed. Absent on success.",
+  "properties": {
+    "code": {
+      "description": "JSON-RPC error code for this failure.",
+      "maximum": 9007199254740991,
+      "minimum": -9007199254740991,
+      "type": "integer"
+    },
+    "data": {
+      "additionalProperties": {},
+      "properties": {
+        "reason": {
+          "description": "Machine-readable failure mode. Declared by this tool: `canvas_not_found`: canvas_id does not match any registered DataCanvas session (expired, wrong session, or canvas disabled) Other values are possible when a failure originates below the handler.",
+          "examples": [
+            "canvas_not_found"
+          ],
+          "type": "string"
+        },
+        "recovery": {
+          "additionalProperties": {},
+          "description": "Actionable next step for the caller.",
+          "properties": {
+            "hint": {
+              "type": "string"
+            }
+          },
+          "required": [
+            "hint"
+          ],
+          "type": "object"
+        },
+        "retryable": {
+          "description": "Whether retrying may succeed.",
+          "type": "boolean"
+        }
+      },
+      "type": "object"
+    },
+    "message": {
+      "description": "Human-readable description of what went wrong.",
+      "type": "string"
+    }
+  },
+  "required": [
+    "code",
+    "message"
+  ],
+  "type": "object"
+}

Removed value: -[
-  "canvas_id",
-  "tables",
-  "table_count"
-]

Previous value: -"http://json-schema.org/draft-07/schema#"New value: +"https://json-schema.org/draft/2020-12/schema"

Added value: +false

Previous value: -"http://json-schema.org/draft-07/schema#"New value: +"https://json-schema.org/draft/2020-12/schema"

Added value: +[
+  {
+    "not": {
+      "required": [
+        "error"
+      ]
+    },
+    "required": [
+      "rows",
+      "row_count",
+      "truncated"
+    ]
+  },
+  {
+    "required": [
+      "error"
+    ]
+  }
+]

Added value: +{
+  "additionalProperties": {},
+  "description": "Present when the call failed. Absent on success.",
+  "properties": {
+    "code": {
+      "description": "JSON-RPC error code for this failure.",
+      "maximum": 9007199254740991,
+      "minimum": -9007199254740991,
+      "type": "integer"
+    },
+    "data": {
+      "additionalProperties": {},
+      "properties": {
+        "reason": {
+          "description": "Machine-readable failure mode. Declared by this tool: `canvas_not_found`: canvas_id does not match any registered DataCanvas session (expired, wrong session, or canvas disabled) `missing_table`: The canvas exists but sql references a table that is not staged on it — the table expired, was dropped, or the name is wrong `invalid_sql`: sql is not a single SELECT statement (a leading WITH … SELECT counts as one), or it is SELECT-shaped but fails to prepare — unknown column, unknown function, or a syntax error `sql_not_permitted`: sql parses as a SELECT but the read-only gate refuses it — it calls an external-data or PRAGMA table function, reads a system catalog, or plans an operator outside the read-only allowlist Other values are possible when a failure originates below the handler.",
+          "examples": [
+            "canvas_not_found",
+            "missing_table",
+            "invalid_sql",
+            "sql_not_permitted"
+          ],
+          "type": "string"
+        },
+        "recovery": {
+          "additionalProperties": {},
+          "description": "Actionable next step for the caller.",
+          "properties": {
+            "hint": {
+              "type": "string"
+            }
+          },
+          "required": [
+            "hint"
+          ],
+          "type": "object"
+        },
+        "retryable": {
+          "description": "Whether retrying may succeed.",
+          "type": "boolean"
+        }
+      },
+      "type": "object"
+    },
+    "message": {
+      "description": "Human-readable description of what went wrong.",
+      "type": "string"
+    }
+  },
+  "required": [
+    "code",
+    "message"
+  ],
+  "type": "object"
+}

Removed value: -[
-  "rows",
-  "row_count",
-  "truncated"
-]

Previous value: -"http://json-schema.org/draft-07/schema#"New value: +"https://json-schema.org/draft/2020-12/schema"

Added value: +false

Previous value: -"http://json-schema.org/draft-07/schema#"New value: +"https://json-schema.org/draft/2020-12/schema"

Added value: +[
+  {
+    "not": {
+      "required": [
+        "error"
+      ]
+    },
+    "required": [
+      "dataflow_id",
+      "agency_id",
+      "version",
+      "name",
+      "key_format",
+      "dimensions",
+      "source"
+    ]
+  },
+  {
+    "required": [
+      "error"
+    ]
+  }
+]

Added value: +{
+  "additionalProperties": {},
+  "description": "Present when the call failed. Absent on success.",
+  "properties": {
+    "code": {
+      "description": "JSON-RPC error code for this failure.",
+      "maximum": 9007199254740991,
+      "minimum": -9007199254740991,
+      "type": "integer"
+    },
+    "data": {
+      "additionalProperties": {},
+      "properties": {
+        "reason": {
+          "description": "Machine-readable failure mode. Declared by this tool: `dataflow_not_found`: dataflow_id does not match any known dataflow on api.imf.org `structure_unavailable`: api.imf.org returns non-200 on the DSD endpoint `dataflow_list_unavailable`: The dataflow catalog that dataflow_id is resolved against could not be fetched — fires before the DSD lookup is attempted Other values are possible when a failure originates below the handler.",
+          "examples": [
+            "dataflow_not_found",
+            "structure_unavailable",
+            "dataflow_list_unavailable"
+          ],
+          "type": "string"
+        },
+        "recovery": {
+          "additionalProperties": {},
+          "description": "Actionable next step for the caller.",
+          "properties": {
+            "hint": {
+              "type": "string"
+            }
+          },
+          "required": [
+            "hint"
+          ],
+          "type": "object"
+        },
+        "retryable": {
+          "description": "Whether retrying may succeed.",
+          "type": "boolean"
+        }
+      },
+      "type": "object"
+    },
+    "message": {
+      "description": "Human-readable description of what went wrong.",
+      "type": "string"
+    }
+  },
+  "required": [
+    "code",
+    "message"
+  ],
+  "type": "object"
+}

Removed value: -[
-  "dataflow_id",
-  "agency_id",
-  "version",
-  "name",
-  "key_format",
-  "dimensions",
-  "source"
-]

Previous value: -"http://json-schema.org/draft-07/schema#"New value: +"https://json-schema.org/draft/2020-12/schema"

Added value: +false

Previous value: -"http://json-schema.org/draft-07/schema#"New value: +"https://json-schema.org/draft/2020-12/schema"

Added value: +[
+  {
+    "not": {
+      "required": [
+        "error"
+      ]
+    },
+    "required": [
+      "dataflows",
+      "total_count",
+      "returned_count",
+      "offset"
+    ]
+  },
+  {
+    "required": [
+      "error"
+    ]
+  }
+]

Added value: +{
+  "additionalProperties": {},
+  "description": "Present when the call failed. Absent on success.",
+  "properties": {
+    "code": {
+      "description": "JSON-RPC error code for this failure.",
+      "maximum": 9007199254740991,
+      "minimum": -9007199254740991,
+      "type": "integer"
+    },
+    "data": {
+      "additionalProperties": {},
+      "properties": {
+        "reason": {
+          "description": "Machine-readable failure mode. Declared by this tool: `dataflow_list_unavailable`: The IMF SDMX structure endpoint that backs the dataflow catalog did not return a usable response Other values are possible when a failure originates below the handler.",
+          "examples": [
+            "dataflow_list_unavailable"
+          ],
+          "type": "string"
+        },
+        "recovery": {
+          "additionalProperties": {},
+          "description": "Actionable next step for the caller.",
+          "properties": {
+            "hint": {
+              "type": "string"
+            }
+          },
+          "required": [
+            "hint"
+          ],
+          "type": "object"
+        },
+        "retryable": {
+          "description": "Whether retrying may succeed.",
+          "type": "boolean"
+        }
+      },
+      "type": "object"
+    },
+    "message": {
+      "description": "Human-readable description of what went wrong.",
+      "type": "string"
+    }
+  },
+  "required": [
+    "code",
+    "message"
+  ],
+  "type": "object"
+}

Removed value: -[
-  "dataflows",
-  "total_count",
-  "returned_count",
-  "offset"
-]

Previous value: -"http://json-schema.org/draft-07/schema#"New value: +"https://json-schema.org/draft/2020-12/schema"

Added value: +false

Previous value: -"http://json-schema.org/draft-07/schema#"New value: +"https://json-schema.org/draft/2020-12/schema"

Added value: +[
+  {
+    "not": {
+      "required": [
+        "error"
+      ]
+    },
+    "required": [
+      "dataflow_id",
+      "key",
+      "observations",
+      "series_attributes",
+      "observation_count",
+      "truncated",
+      "source"
+    ]
+  },
+  {
+    "required": [
+      "error"
+    ]
+  }
+]

Added value: +{
+  "additionalProperties": {},
+  "description": "Present when the call failed. Absent on success.",
+  "properties": {
+    "code": {
+      "description": "JSON-RPC error code for this failure.",
+      "maximum": 9007199254740991,
+      "minimum": -9007199254740991,
+      "type": "integer"
+    },
+    "data": {
+      "additionalProperties": {},
+      "properties": {
+        "reason": {
+          "description": "Machine-readable failure mode. Declared by this tool: `dataflow_not_found`: dataflow_id does not match any known dataflow on api.imf.org `no_data`: Key is structurally valid but the dataflow holds no series for this code combination, or the dataflow publishes no series at all `no_data_in_range`: The key returned observations but start_period/end_period excluded every one of them `key_dimension_mismatch`: Number of dot-separated segments in key does not match the dataflow's DSD dimension count `empty_key_segment`: A dot-separated position in key is empty or blank, which matches no series upstream `invalid_period_format`: start_period or end_period is not one of the recognized period formats `invalid_period_range`: start_period is later than end_period `structure_unavailable`: api.imf.org returns non-200 on the data endpoint `dataflow_list_unavailable`: The dataflow catalog that dataflow_id is resolved against could not be fetched — fires before the DSD and data lookups are attempted Other values are possible when a failure originates below the handler.",
+          "examples": [
+            "dataflow_not_found",
+            "no_data",
+            "no_data_in_range",
+            "key_dimension_mismatch",
+            "empty_key_segment",
+            "invalid_period_format",
+            "invalid_period_range",
+            "structure_unavailable",
+            "dataflow_list_unavailable"
+          ],
+          "type": "string"
+        },
+        "recovery": {
+          "additionalProperties": {},
+          "description": "Actionable next step for the caller.",
+          "properties": {
+            "hint": {
+              "type": "string"
+            }
+          },
+          "required": [
+            "hint"
+          ],
+          "type": "object"
+        },
+        "retryable": {
+          "description": "Whether retrying may succeed.",
+          "type": "boolean"
+        }
+      },
+      "type": "object"
+    },
+    "message": {
+      "description": "Human-readable description of what went wrong.",
+      "type": "string"
+    }
+  },
+  "required": [
+    "code",
+    "message"
+  ],
+  "type": "object"
+}

Removed value: -[
-  "dataflow_id",
-  "key",
-  "observations",
-  "series_attributes",
-  "observation_count",
-  "truncated",
-  "source"
-]

Previous value: -"Unit of measure, e.g. Percent, USD."New value: +"Unit of measure as the upstream code, e.g. PT (percent), USD, XDC (domestic currency), NUM (count). Null when the response carries no unit for the series — many dataflows publish none."

Previous value: -"Per-series attributes, one entry per distinct series_key in the result. Present only when the query resolved to more than one series; a single-series query carries its values in series_attributes instead. Scale differs across series in one query — WEO NGDPD is scale 9 while NGDP_RPCH is unscaled — so interpret each series against its own entry."New value: +"Per-series attributes, one entry per distinct series_key in the result. Present only when the query resolved to more than one series; a single-series query carries its values in series_attributes instead. Unit and scale differ across series in one query — WEO NGDPD is USD at scale 9 while NGDP_RPCH is PT unscaled — so interpret each series against its own entry."

Previous value: -"Unit of measure for this series, e.g. Percent."New value: +"Unit of measure for this series as the upstream code, e.g. PT (percent), USD, XDC (domestic currency). Null when the response carries none for it."

Previous value: -"This dataflow's own description, matching what imf_list_databases reports for the same id — not the shared DSD's. Absent when the dataflow publishes none."New value: +"This dataflow's own description in full — not the shared DSD's, and not the shortened preview imf_list_databases returns for the same id. Absent when the dataflow publishes none."

Added value: +{
+  "default": 50,
+  "description": "Maximum dataflows to return in this call. Default 50, ceiling 200; total_count reports how many matched, so a partial page is always recognizable as one.",
+  "maximum": 200,
+  "minimum": 1,
+  "type": "integer"
+}

Added value: +{
+  "default": 0,
+  "description": "Number of matching dataflows to skip before this page. Combine with limit to page through a broad or unfiltered catalog.",
+  "maximum": 9007199254740991,
+  "minimum": 0,
+  "type": "integer"
+}

Added value: +{
+  "description": "The limit that bounded this page.",
+  "type": "number"
+}

Previous value: -"Matching dataflows; pass the id to imf_get_database to resolve dimension codelists."New value: +"This page of matching dataflows; pass the id to imf_get_database to resolve dimension codelists."

Previous value: -"Extended description of the dataflow, if available."New value: +"Short description, cut to 200 characters and ended with … when longer. imf_get_database and the imf://database/{dataflow_id} resource return the full text."

Previous value: -"Populated when the filter matches nothing — explains why and suggests next steps."New value: +"Populated when the filter matches nothing, or when matches remain beyond this page — explains why and names the next offset to request."

Added value: +{
+  "description": "Number of matching dataflows skipped before this page.",
+  "type": "number"
+}

Added value: +{
+  "description": "Dataflows in this page — the length of dataflows.",
+  "type": "number"
+}

Added value: +{
+  "description": "Dataflows returned in this page.",
+  "type": "number"
+}

Previous value: -"Total number of matching dataflows returned."New value: +"Dataflows matching filter and include_vintages, before limit and offset are applied. Exceeds returned_count when more pages remain."

Added value: +{
+  "description": "True when matching dataflows remain beyond this page.",
+  "type": "boolean"
+}

Previous value: -[
-  "dataflows",
-  "total_count"
-]New value: +[
+  "dataflows",
+  "total_count",
+  "returned_count",
+  "offset"
+]

Previous value: -"Series-level attributes (unit, scale, decimals)."New value: +"Attributes of the first series in the result — the same series as series_metadata[0]. A key with + or * resolves to several series whose scale and unit differ, and this field describes only the first of them: read series_metadata for the rest, and never apply these values to another series_key."

Previous value: -"Scale multiplier, e.g. Billions."New value: +"Scale multiplier as the upstream code, e.g. 9 for billions. \"0\" means no multiplier — the values are unscaled."

Added value: +{
+  "description": "Per-series attributes, one entry per distinct series_key in the result. Present only when the query resolved to more than one series; a single-series query carries its values in series_attributes instead. Scale differs across series in one query — WEO NGDPD is scale 9 while NGDP_RPCH is unscaled — so interpret each series against its own entry.",
+  "items": {
+    "additionalProperties": false,
+    "description": "Unit, scale, and decimals for one series in the result.",
+    "properties": {
+      "decimals": {
+        "anyOf": [
+          {
+            "type": "number"
+          },
+          {
+            "type": "null"
+          }
+        ],
+        "description": "Number of decimal places shown for this series."
+      },
+      "scale": {
+        "anyOf": [
+          {
+            "type": "string"
+          },
+          {
+            "type": "null"
+          }
+        ],
+        "description": "Scale multiplier for this series as the upstream code, e.g. 9 for billions. \"0\" means no multiplier."
+      },
+      "series_key": {
+        "description": "Series these attributes belong to, matching observations[].series_key.",
+        "type": "string"
+      },
+      "unit": {
+        "anyOf": [
+          {
+            "type": "string"
+          },
+          {
+            "type": "null"
+          }
+        ],
+        "description": "Unit of measure for this series, e.g. Percent."
+      }
+    },
+    "required": [
+      "series_key",
+      "unit",
+      "scale",
+      "decimals"
+    ],
+    "type": "object"
+  },
+  "type": "array"
+}

Previous value: -"Extended description, if available."New value: +"This dataflow's own description, matching what imf_list_databases reports for the same id — not the shared DSD's. Absent when the dataflow publishes none."

Previous value: -"End of time range (inclusive). Same format as start_period, and must be greater than or equal to start_period. Observations after this period are excluded from the result."New value: +"End of time range (inclusive). Same formats as start_period, and must not be earlier than it. The bound covers the whole period it names, so end_period 2023 admits 2023-M12 and 2023-Q4. Observations after this period are excluded from the result."

Previous value: -"Dot-separated dimension codes in DSD keyPosition order. Call imf_get_database to get key_format and valid codes first. Use + to specify multiple codes (e.g. USA+GBR.NGDP_RPCH.A). Country codes are ISO 3-letter: USA not US, GBR not GB, DEU not DE."New value: +"Dot-separated dimension codes in DSD keyPosition order. Call imf_get_database to get key_format and valid codes first. Use + to combine codes at one position (e.g. USA+GBR.NGDP_RPCH.A). Use * to match every code at a position — *.NGDP_RPCH.A returns the indicator for all countries, and CAN.*.A every indicator for Canada. Every position needs a code or a *; an empty segment (USA..A) is rejected. Country codes are ISO 3-letter: USA not US, GBR not GB, DEU not DE."

Previous value: -"Start of time range (inclusive). Format matches the dataflow frequency: YYYY (annual), YYYY-QN (quarterly, e.g. 2023-Q1), YYYY-MM (monthly). Observations before this period are excluded from the result."New value: +"Start of time range (inclusive). Accepts any of YYYY (annual), YYYY-SN (semi-annual, e.g. 2023-S1), YYYY-QN (quarterly, e.g. 2023-Q1), YYYY-MM (monthly), or YYYY-MM-DD (daily), whatever the dataflow's frequency. The bound covers the whole period it names, so start_period 2023 admits 2023-M01 and 2023-Q1. Observations before this period are excluded from the result."

Added value: +{
+  "description": "Populated when a period bound was set but some observations carry a time_period label the range filter does not recognize — those rows are returned unfiltered, so the requested range did not apply to them.",
+  "type": "string"
+}

Previous value: -"Time label as emitted by the upstream API. Annual: YYYY (e.g. 2023). Quarterly: YYYY-QN (e.g. 2023-Q1). Monthly: YYYY-MNN (e.g. 2023-M01, not YYYY-MM). start_period/end_period accept both YYYY-MM and YYYY-MNN for monthly comparisons."New value: +"Time label as emitted by the upstream API. Annual: YYYY (e.g. 2023). Semi-annual: YYYY-SN (e.g. 2023-S1). Quarterly: YYYY-QN (e.g. 2023-Q1). Monthly: YYYY-MNN (e.g. 2023-M01, not YYYY-MM). Daily: YYYY-MM-DD (e.g. 2023-01-05). Every one of these is also accepted as a start_period/end_period bound, so a label from this field can be passed straight back in."

Added value: +{
+  "description": "Echo of the codelist_filter that produced this result. Absent when no filter was applied — an empty codelist then means the codelist could not be resolved, not that the filter missed.",
+  "type": "string"
+}

Previous value: -"Valid codes for this dimension. Up to 50 entries shown when no codelist_filter is set; use codelist_filter to search large codelists or the imf://database resource for the full list."New value: +"Valid codes for this dimension. Up to 50 entries shown when no codelist_filter is set; use codelist_filter to search large codelists or the imf://database resource for the full list. Empty means the filter matched nothing when codelist_filter is echoed back, and that the codelist could not be resolved when it is not — see notice."

Previous value: -"Human-readable dimension name."New value: +"Human-readable dimension label from the DSD concept scheme, e.g. Weight Type for WGT_TYPE. Falls back to the dimension id when the structure names no concept."

Added value: +{
+  "description": "Populated when a codelist_filter matched no entries anywhere, or when a dimension has no resolvable codelist — the two produce the same empty array and need opposite next steps.",
+  "type": "string"
+}

Previous value: -"Read-only SQL SELECT statement. Must start with SELECT. Reference tables by the names returned by imf_dataframe_describe. Example: SELECT time_period, value FROM spilled_abc123 WHERE time_period >= '2010' ORDER BY time_period."New value: +"Read-only SQL SELECT statement — exactly one statement, starting with SELECT or with a WITH … SELECT common table expression. Reference tables by the names returned by imf_dataframe_describe. Example: SELECT time_period, value FROM spilled_abc123 WHERE time_period >= '2010' ORDER BY time_period."

Previous value: -"Total matching rows before the cap — may exceed rows.length."New value: +"Number of rows materialized in rows. Equals the canvas row limit when truncated is true — DataCanvas does not report a pre-cap total, so this is never larger than rows.length."

Added value: +{
+  "description": "True when the query matched more rows than the canvas row limit and the result was capped. Page the remainder with a stable ORDER BY plus LIMIT/OFFSET, or narrow the query with WHERE or aggregation.",
+  "type": "boolean"
+}

Previous value: -[
-  "rows",
-  "row_count"
-]New value: +[
+  "rows",
+  "row_count",
+  "truncated"
+]

Previous value: -"End of time range (inclusive). Same format as start_period. Observations after this period are excluded from the result."New value: +"End of time range (inclusive). Same format as start_period, and must be greater than or equal to start_period. Observations after this period are excluded from the result."

Added value: +{
+  "description": "Version of the underlying data structure definition (DSD) that backs this dataflow. Differs from version when the dataflow references a shared DSD (e.g. IIP → DSD_BOP at 24.0.0).",
+  "type": "string"
+}

Added value: +{
+  "description": "Identifier of the underlying DSD, e.g. DSD_BOP. Several dataflows can share one DSD.",
+  "type": "string"
+}

Added value: +{
+  "description": "Optional case-insensitive substring to search within each dimension's codelist (code ID and name). When set, returns all matching entries per dimension instead of the first-50 window — useful for large codelists like WEO INDICATOR (145 entries). Example: \"CPI\" or \"PCPIPCH\" surfaces consumer price index codes without hitting the 50-entry cap.",
+  "type": "string"
+}

Previous value: -"Valid codes for this dimension. Up to 50 entries shown; full list available via the imf://database resource."New value: +"Valid codes for this dimension. Up to 50 entries shown when no codelist_filter is set; use codelist_filter to search large codelists or the imf://database resource for the full list."

Previous value: -"Optional name or ID substring to filter results. Case-insensitive. Example: \"exchange rate\" returns ER and related dataflows."New value: +"Optional name, ID, or description substring to filter results. Case-insensitive. Example: \"exchange rate\" returns ER and related dataflows."

Previous value: -"Requested end of time range. Same format as start_period. See start_period note: the API returns the full series; this parameter is passed through but may not filter observations."New value: +"End of time range (inclusive). Same format as start_period. Observations after this period are excluded from the result."

Previous value: -"Requested start of time range. Format matches the dataflow frequency: YYYY (annual), YYYY-QN (quarterly, e.g. 2023-Q1), YYYY-MM (monthly). Note: the IMF SDMX 3.0 compact JSON endpoint returns the full available series regardless of this parameter — observations outside the requested range may still appear."New value: +"Start of time range (inclusive). Format matches the dataflow frequency: YYYY (annual), YYYY-QN (quarterly, e.g. 2023-Q1), YYYY-MM (monthly). Observations before this period are excluded from the result."

Previous value: -"Time label, e.g. 2023 or 2023-Q1 or 2023-01."New value: +"Time label as emitted by the upstream API. Annual: YYYY (e.g. 2023). Quarterly: YYYY-QN (e.g. 2023-Q1). Monthly: YYYY-MNN (e.g. 2023-M01, not YYYY-MM). start_period/end_period accept both YYYY-MM and YYYY-MNN for monthly comparisons."