EU Trade Explorer

Get Pattern Shift

get_pattern_shift

Before/after trade-pattern shift around a split point (query.midpoint): for each entity, compares average quantity and price before vs. after, and returns scatter points (quantity-change % vs. price-change %) with quadrant labels -- top-right = demand-driven growth, top-left = supply constraint/monopoly risk, bottom-right = dumping/oversupply risk, bottom-left = market contraction. Suggested workflow: spot a shock date via get_supply_shocks / get_price_shocks first, then set it as query.midpoint here.

Input Schema

TableJSON Schema

Name	Required	Description	Default
`query`	Yes	The product/reporter/partner-set/period/frequency slice to query -- the same request body every tradedashboard.eu analytical endpoint takes. See its own field descriptions (product, reporter, partner_set, period_start, period_end, frequency, n_top, ...) for details; only `product` is required, everything else has a sensible default.
`compact`	No	If true, condense long numeric time series (more than ~6 points -- typically monthly/quarterly windows or wide multi-partner/multi-period breakdowns) into summary statistics (first, last, min, max, mean, pct_change) instead of returning every data point. Leave false for full-fidelity series (e.g. to actually plot a chart); set true when you just need the headline trend and want to save context.

Output Schema

TableJSON Schema

Name	Required	Description	Default
No arguments

Schema Changelog

Changes observed during successful MCP inspections.

Changed9 schema fields changedAug 5, 2026

removedInput schema / $defs

Removed value: -{
-  "DashboardQuery": {
-    "description": "Shared request body for every analytical endpoint.\n\nOne product (or a list of products to aggregate), one reporter (or group of\nreporters), a partner set, a period window and a frequency fully describe a\nslice of Eurostat Comext/PRODCOM data. Individual endpoints read extra,\nendpoint-specific options from the query string (e.g. ``entity_level``,\n``flow``, ``partner``) rather than from this body.",
-    "properties": {
-      "frequency": {
-        "default": "quarter",
-        "description": "Resampling frequency for the series: 'month', 'quarter' or 'year'.",
-        "title": "Frequency",
-        "type": "string"
-      },
-      "include_other": {
-        "default": true,
-        "description": "Bundle entities outside the top-N into a single 'Other' bucket.",
-        "title": "Include Other",
-        "type": "boolean"
-      },
-      "lang": {
-        "default": "en",
-        "description": "Language for translated labels in the response (en, de, fr, es, it, ro).",
-        "title": "Lang",
-        "type": "string"
-      },
-      "midpoint": {
-        "anyOf": [
-          {
-            "type": "string"
-          },
-          {
-            "type": "null"
-          }
-        ],
-        "default": null,
-        "description": "Split point 'YYYY-MM' for the Pattern Shifts tab: the window is cut in two here and the before/after change per entity is reported. Defaults to the middle of the period when omitted.",
-        "title": "Midpoint"
-      },
-      "n_top": {
-        "default": 7,
-        "description": "Number of top entities (by volume/value) to break out individually in charts.",
-        "title": "N Top",
-        "type": "integer"
-      },
-      "partner_set": {
-        "default": "non-EU countries",
-        "description": "Named partner preset, e.g. 'non-EU countries', 'EU countries', 'all countries', or a predefined partner group.",
-        "title": "Partner Set",
-        "type": "string"
-      },
-      "partners": {
-        "anyOf": [
-          {
-            "items": {
-              "type": "string"
-            },
-            "type": "array"
-          },
-          {
-            "type": "null"
-          }
-        ],
-        "default": null,
-        "description": "Explicit partner-country list that overrides 'partner_set' when present.",
-        "title": "Partners"
-      },
-      "period_end": {
-        "description": "Inclusive end of the analysis window, ISO month 'YYYY-MM'. Defaults to roughly three months ago — the latest period Eurostat typically has fully reported.",
-        "title": "Period End",
-        "type": "string"
-      },
-      "period_start": {
-        "default": "2015-01",
-        "description": "Inclusive start of the analysis window, ISO month 'YYYY-MM'.",
-        "title": "Period Start",
-        "type": "string"
-      },
-      "prodcom_code": {
-        "anyOf": [
-          {
-            "type": "string"
-          },
-          {
-            "type": "null"
-          }
-        ],
-        "default": null,
-        "description": "Specific PRODCOM dataset code to pin for the Net Import Reliance and Trade Intensity tabs, when a single CN code maps to several. Ignored elsewhere.",
-        "title": "Prodcom Code"
-      },
-      "product": {
-        "anyOf": [
-          {
-            "type": "string"
-          },
-          {
-            "items": {
-              "type": "string"
-            },
-            "type": "array"
-          }
-        ],
-        "description": "Combined Nomenclature customs code(s), 2–8 digits, or the literal 'TOTAL' meta-aggregate (all products combined). Pass a list to aggregate several codes: their volumes are summed and prices volume-weighted across every tab — except the Cross-section views, which keep each code separate.",
-        "examples": [
-          "3801",
-          [
-            "0901",
-            "0902"
-          ],
-          "TOTAL"
-        ],
-        "title": "Product"
-      },
-      "remove_outliers": {
-        "default": true,
-        "description": "Drop extreme unit-price outliers before computing weighted-average prices.",
-        "title": "Remove Outliers",
-        "type": "boolean"
-      },
-      "reporter": {
-        "default": "European Union",
-        "description": "Declaring entity: an EU member state, an EU candidate country, Northern Ireland ('XI'), or one of the three aggregate presets ('European Union', 'Euro area', 'EU candidate countries'), or a predefined reporter group name.",
-        "title": "Reporter",
-        "type": "string"
-      },
-      "reporter_members": {
-        "anyOf": [
-          {
-            "items": {
-              "type": "string"
-            },
-            "type": "array"
-          },
-          {
-            "type": "null"
-          }
-        ],
-        "default": null,
-        "description": "Explicit member countries for a custom reporter group. Each entry must be an EU member state, EU candidate country, or Northern Ireland. When more than one member is supplied the frame is aggregated into a synthetic group named after 'reporter'.",
-        "title": "Reporter Members"
-      }
-    },
-    "required": [
-      "product"
-    ],
-    "title": "DashboardQuery",
-    "type": "object"
-  }
-}

addedInput schema / additionalProperties
```
Added value: +false
```
removedInput schema / properties / compact / title
```
Removed value: -"Compact"
```
removedInput schema / properties / query / $ref
```
Removed value: -"#/$defs/DashboardQuery"
```

addedInput schema / properties / query / properties

Added value: +{
+  "frequency": {
+    "default": "quarter",
+    "description": "Resampling frequency for the series: 'month', 'quarter' or 'year'.",
+    "type": "string"
+  },
+  "include_other": {
+    "default": true,
+    "description": "Bundle entities outside the top-N into a single 'Other' bucket.",
+    "type": "boolean"
+  },
+  "lang": {
+    "default": "en",
+    "description": "Language for translated labels in the response (en, de, fr, es, it, ro).",
+    "type": "string"
+  },
+  "midpoint": {
+    "anyOf": [
+      {
+        "type": "string"
+      },
+      {
+        "type": "null"
+      }
+    ],
+    "default": null,
+    "description": "Split point 'YYYY-MM' for the Pattern Shifts tab: the window is cut in two here and the before/after change per entity is reported. Defaults to the middle of the period when omitted."
+  },
+  "n_top": {
+    "default": 7,
+    "description": "Number of top entities (by volume/value) to break out individually in charts.",
+    "type": "integer"
+  },
+  "partner_set": {
+    "default": "non-EU countries",
+    "description": "Named partner preset, e.g. 'non-EU countries', 'EU countries', 'all countries', or a predefined partner group.",
+    "type": "string"
+  },
+  "partners": {
+    "anyOf": [
+      {
+        "items": {
+          "type": "string"
+        },
+        "type": "array"
+      },
+      {
+        "type": "null"
+      }
+    ],
+    "default": null,
+    "description": "Explicit partner-country list that overrides 'partner_set' when present."
+  },
+  "period_end": {
+    "description": "Inclusive end of the analysis window, ISO month 'YYYY-MM'. Defaults to roughly three months ago — the latest period Eurostat typically has fully reported.",
+    "type": "string"
+  },
+  "period_start": {
+    "default": "2015-01",
+    "description": "Inclusive start of the analysis window, ISO month 'YYYY-MM'.",
+    "type": "string"
+  },
+  "prodcom_code": {
+    "anyOf": [
+      {
+        "type": "string"
+      },
+      {
+        "type": "null"
+      }
+    ],
+    "default": null,
+    "description": "Specific PRODCOM dataset code to pin for the Net Import Reliance and Trade Intensity tabs, when a single CN code maps to several. Ignored elsewhere."
+  },
+  "product": {
+    "anyOf": [
+      {
+        "type": "string"
+      },
+      {
+        "items": {
+          "type": "string"
+        },
+        "type": "array"
+      }
+    ],
+    "description": "Combined Nomenclature customs code(s), 2–8 digits, or the literal 'TOTAL' meta-aggregate (all products combined). Pass a list to aggregate several codes: their volumes are summed and prices volume-weighted across every tab — except the Cross-section views, which keep each code separate.",
+    "examples": [
+      "3801",
+      [
+        "0901",
+        "0902"
+      ],
+      "TOTAL"
+    ]
+  },
+  "remove_outliers": {
+    "default": true,
+    "description": "Drop extreme unit-price outliers before computing weighted-average prices.",
+    "type": "boolean"
+  },
+  "reporter": {
+    "default": "European Union",
+    "description": "Declaring entity: an EU member state, an EU candidate country, Northern Ireland ('XI'), or one of the three aggregate presets ('European Union', 'Euro area', 'EU candidate countries'), or a predefined reporter group name.",
+    "type": "string"
+  },
+  "reporter_members": {
+    "anyOf": [
+      {
+        "items": {
+          "type": "string"
+        },
+        "type": "array"
+      },
+      {
+        "type": "null"
+      }
+    ],
+    "default": null,
+    "description": "Explicit member countries for a custom reporter group. Each entry must be an EU member state, EU candidate country, or Northern Ireland. When more than one member is supplied the frame is aggregated into a synthetic group named after 'reporter'."
+  }
+}

addedInput schema / properties / query / required
```
Added value: +[
+  "product"
+]
```
addedInput schema / properties / query / type
```
Added value: +"object"
```

removedInput schema / title

Removed value: -"get_pattern_shiftArguments"

changedOutput schema / (root)

Previous value: -nullNew value: +{
+  "additionalProperties": true,
+  "type": "object"
+}

First observedJul 21, 2026

TDQS

A4.5/5.0

Behavior4/5

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

With no annotations, the description carries the full burden. It discloses the before/after comparison logic and the meaning of each quadrant, which is essential behavioral detail. It does not mention limitations or data requirements, but the output schema and full parameter descriptions mitigate this.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is two dense sentences with no redundancy. It front-loads the core purpose and follows up with a practical workflow, making every part earn its place.

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

Completeness5/5

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

Given the tool's complexity, the output schema, and full parameter descriptions, the description covers the essential gaps: what the tool does, how to interpret results, and how it relates to sibling tools. It is complete enough for an agent to select and invoke correctly.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100% for top-level parameters, and query subfields all have descriptions, so the baseline is 3. The description adds value by explicitly explaining that query.midpoint is the split point and how it fits into the workflow, which goes beyond the schema's field description.

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?

The description clearly states a specific verb ('compares') and resource ('average quantity and price before vs. after') and defines the output (scatter points with quadrant labels). It distinguishes itself from siblings by framing it as a post-shock analysis step, not a shock detector.

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

Usage Guidelines4/5

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

The 'Suggested workflow' explicitly tells the agent to use get_supply_shocks/get_price_shocks first and then set the shock date as query.midpoint. This gives clear when-to-use context, though it does not explicitly list alternative tools to avoid.

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

All EU Trade Explorer tools Inspect

Try in Browser

One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources

Need Help?