Skip to main content
Glama

Nansen

by io.github.nansen-ai
OverviewDiscussionsAdmin

Checking prediction market trades

prediction_market_trades
Read-only

Recent trades for a Polymarket market.

When to use:

  • Source of truth for recent fills and latest trade-tape pricing.

  • Do not overwrite recent trade prices with older OHLCV candles.

Key fields:

  • Share Size is quantity; Value USD is dollar value.

  • Each row is one visible trade leg — Value USD applies to that row, not the whole transaction hash.

Pitfalls:

  • Large visible trades do not by themselves identify smart money or institutions.

Prerequisites: If marketId is unknown, call prediction_market_lookup first.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
requestYes

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault
resultYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changed
    • changedInput schema / properties / request / anyOf
      Previous value: -[
-  {
-    "additionalProperties": true,
-    "type": "object"
-  },
-  {
-    "additionalProperties": false,
-    "description": "Request for recent market trades.",
-    "properties": {
-      "dateRange": {
-        "anyOf": [
-          {
-            "description": "Date range via tokens or dates.\nTokens: NOW, XMIN_AGO, XD_AGO, XH_AGO; THIS_YEAR_START, THIS_QUARTER_START, THIS_MONTH_START, THIS_WEEK_START, TODAY_START; LAST_WEEK_START/END, LAST_MONTH_START/END, LAST_QUARTER_START/END, LAST_YEAR_START/END.\nWeek starts Monday. Quarters are calendar. Dates: YYYY-MM-DD or ___-MM-DD (year omitted).\nPlease check detailed system instructions for more information.",
-            "properties": {
-              "from": {
-                "description": "Start value: token (see above) or date (YYYY-MM-DD or ___-MM-DD).",
-                "type": "string"
-              },
-              "to": {
-                "description": "End value: token (see above) or date (YYYY-MM-DD or ___-MM-DD).",
-                "type": "string"
-              }
-            },
-            "required": [
-              "from",
-              "to"
-            ],
-            "type": "object"
-          },
-          {
-            "type": "null"
-          }
-        ],
-        "default": null,
-        "description": "Optional date range for market trades. Defaults to the last 7 days."
-      },
-      "marketId": {
-        "description": "Numeric Polymarket market ID (e.g. '654412'). Obtain this from the prediction_market_screener tool.",
-        "maxLength": 100,
-        "minLength": 1,
-        "type": "string"
-      },
-      "page": {
-        "default": 1,
-        "description": "Page number for paginated results.",
-        "minimum": 1,
-        "type": "integer"
-      }
-    },
-    "required": [
-      "marketId"
-    ],
-    "type": "object"
-  }
-]New value: +[
+  {
+    "additionalProperties": true,
+    "type": "object"
+  },
+  {
+    "additionalProperties": false,
+    "description": "Request for recent market trades.",
+    "properties": {
+      "dateRange": {
+        "anyOf": [
+          {
+            "description": "Date range via tokens or dates.\nTokens: NOW, ALL_TIME, XMIN_AGO, XD_AGO, XH_AGO; THIS_YEAR_START, THIS_QUARTER_START, THIS_MONTH_START, THIS_WEEK_START, TODAY_START; LAST_WEEK_START/END, LAST_MONTH_START/END, LAST_QUARTER_START/END, LAST_YEAR_START/END.\nALL_TIME is full history. It resolves to 2009-01-03. Use ALL_TIME instead of a very large day count.\nWeek starts Monday. Quarters are calendar. Dates: YYYY-MM-DD or ___-MM-DD (year omitted).\nPlease check detailed system instructions for more information.",
+            "properties": {
+              "from": {
+                "description": "Start value: token (see above) or date (YYYY-MM-DD or ___-MM-DD).",
+                "type": "string"
+              },
+              "to": {
+                "description": "End value: token (see above) or date (YYYY-MM-DD or ___-MM-DD).",
+                "type": "string"
+              }
+            },
+            "required": [
+              "from",
+              "to"
+            ],
+            "type": "object"
+          },
+          {
+            "type": "null"
+          }
+        ],
+        "default": null,
+        "description": "Optional date range for market trades. Defaults to the last 7 days."
+      },
+      "marketId": {
+        "description": "Numeric Polymarket market ID (e.g. '654412'). Obtain this from the prediction_market_screener tool.",
+        "maxLength": 100,
+        "minLength": 1,
+        "type": "string"
+      },
+      "page": {
+        "default": 1,
+        "description": "Page number for paginated results.",
+        "minimum": 1,
+        "type": "integer"
+      }
+    },
+    "required": [
+      "marketId"
+    ],
+    "type": "object"
+  }
+]
  2. Changed3 schema fields changed
    • removedInput schema / $defs
      Removed value: -{
-  "DateRange": {
-    "description": "Date range via tokens or dates.\nTokens: NOW, XMIN_AGO, XD_AGO, XH_AGO; THIS_YEAR_START, THIS_QUARTER_START, THIS_MONTH_START, THIS_WEEK_START, TODAY_START; LAST_WEEK_START/END, LAST_MONTH_START/END, LAST_QUARTER_START/END, LAST_YEAR_START/END.\nWeek starts Monday. Quarters are calendar. Dates: YYYY-MM-DD or ___-MM-DD (year omitted).\nPlease check detailed system instructions for more information.",
-    "properties": {
-      "from": {
-        "description": "Start value: token (see above) or date (YYYY-MM-DD or ___-MM-DD).",
-        "type": "string"
-      },
-      "to": {
-        "description": "End value: token (see above) or date (YYYY-MM-DD or ___-MM-DD).",
-        "type": "string"
-      }
-    },
-    "required": [
-      "from",
-      "to"
-    ],
-    "type": "object"
-  },
-  "PredictionMarketTradesRequest": {
-    "description": "Request for recent market trades.",
-    "properties": {
-      "dateRange": {
-        "anyOf": [
-          {
-            "$ref": "#/$defs/DateRange"
-          },
-          {
-            "type": "null"
-          }
-        ],
-        "default": null,
-        "description": "Optional date range for market trades. Defaults to the last 7 days."
-      },
-      "marketId": {
-        "description": "Numeric Polymarket market ID (e.g. '654412'). Obtain this from the prediction_market_screener tool.",
-        "maxLength": 100,
-        "minLength": 1,
-        "type": "string"
-      },
-      "page": {
-        "default": 1,
-        "description": "Page number for paginated results.",
-        "minimum": 1,
-        "type": "integer"
-      }
-    },
-    "required": [
-      "marketId"
-    ],
-    "type": "object"
-  }
-}
    • addedInput schema / additionalProperties
      Added value: +false
    • changedInput schema / properties / request / anyOf
      Previous value: -[
-  {
-    "additionalProperties": true,
-    "type": "object"
-  },
-  {
-    "$ref": "#/$defs/PredictionMarketTradesRequest"
-  }
-]New value: +[
+  {
+    "additionalProperties": true,
+    "type": "object"
+  },
+  {
+    "additionalProperties": false,
+    "description": "Request for recent market trades.",
+    "properties": {
+      "dateRange": {
+        "anyOf": [
+          {
+            "description": "Date range via tokens or dates.\nTokens: NOW, XMIN_AGO, XD_AGO, XH_AGO; THIS_YEAR_START, THIS_QUARTER_START, THIS_MONTH_START, THIS_WEEK_START, TODAY_START; LAST_WEEK_START/END, LAST_MONTH_START/END, LAST_QUARTER_START/END, LAST_YEAR_START/END.\nWeek starts Monday. Quarters are calendar. Dates: YYYY-MM-DD or ___-MM-DD (year omitted).\nPlease check detailed system instructions for more information.",
+            "properties": {
+              "from": {
+                "description": "Start value: token (see above) or date (YYYY-MM-DD or ___-MM-DD).",
+                "type": "string"
+              },
+              "to": {
+                "description": "End value: token (see above) or date (YYYY-MM-DD or ___-MM-DD).",
+                "type": "string"
+              }
+            },
+            "required": [
+              "from",
+              "to"
+            ],
+            "type": "object"
+          },
+          {
+            "type": "null"
+          }
+        ],
+        "default": null,
+        "description": "Optional date range for market trades. Defaults to the last 7 days."
+      },
+      "marketId": {
+        "description": "Numeric Polymarket market ID (e.g. '654412'). Obtain this from the prediction_market_screener tool.",
+        "maxLength": 100,
+        "minLength": 1,
+        "type": "string"
+      },
+      "page": {
+        "default": 1,
+        "description": "Page number for paginated results.",
+        "minimum": 1,
+        "type": "integer"
+      }
+    },
+    "required": [
+      "marketId"
+    ],
+    "type": "object"
+  }
+]
  3. Added

TDQS

A4.3/5.0
Behavior4/5

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

Annotations already declare readOnlyHint=true and destructiveHint=false, so the safety profile is covered. The description adds real behavioral context beyond that: each row is a single visible trade leg, Value USD applies per-row and not per transaction hash, and visible trade size does not identify smart money. It does not discuss pagination or result limits, which is the only gap.

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 one-line purpose followed by labeled sections, so an agent can scan it quickly. The Key fields and Pitfalls bullets earn their place, though the formatting is slightly verbose relative to the short payload.

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?

An output schema exists, so return-value documentation is unnecessary, and the description covers usage, prerequisites, and interpretation traps. It is nearly complete, lacking only guidance on pagination and how many rows to expect.

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 description coverage is reported at 0%, so the description should carry more of the parameter burden. It does route the agent to prediction_market_lookup for marketId, but never explains the request wrapper, page, or dateRange defaults (default last 7 days lives only in the schema).

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb and resource ('Recent trades for a Polymarket market') and immediately frames it as the source of truth for fills and trade-tape pricing. The line about not overwriting recent trade prices with older OHLCV candles effectively distinguishes it from the sibling prediction_market_ohlcv.

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?

Explicit 'When to use' section plus a hard prerequisite: if marketId is unknown, call prediction_market_lookup first. It also names the failure mode (using stale candles) that selects against the sibling tool.

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

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

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources