Skip to main content
Glama

Nansen

by io.github.nansen-ai
OverviewDiscussionsAdmin

Finding prediction market top holders

prediction_market_top_holders
Read-only

Largest current holders for a Polymarket market.

Key fields:

  • Positions are share balances, not USD notional.

  • Position Value USD is current marked value, not payout at resolution.

  • Side Held is the share side currently held.

Pitfalls:

  • The visible holder table is the source of truth for holder-side concentration — do not infer risk, max loss, or potential profit unless the tool output explicitly provides it.

  • Output summary is based only on shown rows, not the entire holder table.

  • Large visible positions or labels do not by themselves identify smart money unless Nansen smart-money-labelled data supports it.

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 prediction market top holders.",
-    "properties": {
-      "marketId": {
-        "description": "Numeric Polymarket market ID (e.g. '654412'). Obtain this from the prediction_market_screener tool.",
-        "maxLength": 100,
-        "minLength": 1,
-        "type": "string"
-      },
-      "orderBy": {
-        "anyOf": [
-          {
-            "type": "string"
-          },
-          {
-            "type": "null"
-          }
-        ],
-        "default": null,
-        "description": "Optional sort field. Common fields: positionSize, unrealizedPnlUsd, avgEntryPrice."
-      },
-      "orderByDirection": {
-        "default": "desc",
-        "description": "Sort direction when orderBy is provided.",
-        "enum": [
-          "asc",
-          "desc",
-          "ASC",
-          "DESC"
-        ],
-        "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 prediction market top holders.",
+    "properties": {
+      "marketId": {
+        "description": "Numeric Polymarket market ID (e.g. '654412'). Obtain this from the prediction_market_screener tool.",
+        "maxLength": 100,
+        "minLength": 1,
+        "type": "string"
+      },
+      "orderBy": {
+        "anyOf": [
+          {
+            "enum": [
+              "position_size",
+              "unrealized_pnl_usd",
+              "avg_entry_price"
+            ],
+            "type": "string"
+          },
+          {
+            "type": "null"
+          }
+        ],
+        "default": null,
+        "description": "Sort field. Pass an exact value above or None for default ('position_size')."
+      },
+      "orderByDirection": {
+        "default": "DESC",
+        "description": "Sort direction: 'ASC' or 'DESC' (case-insensitive).",
+        "enum": [
+          "ASC",
+          "DESC",
+          "asc",
+          "desc"
+        ],
+        "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 / $defs
      Removed value: -{
-  "PredictionMarketTopHoldersRequest": {
-    "description": "Request for prediction market top holders.",
-    "properties": {
-      "marketId": {
-        "description": "Numeric Polymarket market ID (e.g. '654412'). Obtain this from the prediction_market_screener tool.",
-        "maxLength": 100,
-        "minLength": 1,
-        "type": "string"
-      },
-      "orderBy": {
-        "anyOf": [
-          {
-            "type": "string"
-          },
-          {
-            "type": "null"
-          }
-        ],
-        "default": null,
-        "description": "Optional sort field. Common fields: positionSize, unrealizedPnlUsd, avgEntryPrice."
-      },
-      "orderByDirection": {
-        "default": "desc",
-        "description": "Sort direction when orderBy is provided.",
-        "enum": [
-          "asc",
-          "desc",
-          "ASC",
-          "DESC"
-        ],
-        "type": "string"
-      },
-      "page": {
-        "default": 1,
-        "description": "Page number for paginated results.",
-        "minimum": 1,
-        "type": "integer"
-      }
-    },
-    "required": [
-      "marketId"
-    ],
-    "type": "object"
-  }
-}
    • addedInput schema / additionalProperties
      Added value: +false
    • changedInput schema / properties / request / anyOf
      Previous value: -[
-  {
-    "additionalProperties": true,
-    "type": "object"
-  },
-  {
-    "$ref": "#/$defs/PredictionMarketTopHoldersRequest"
-  }
-]New value: +[
+  {
+    "additionalProperties": true,
+    "type": "object"
+  },
+  {
+    "additionalProperties": false,
+    "description": "Request for prediction market top holders.",
+    "properties": {
+      "marketId": {
+        "description": "Numeric Polymarket market ID (e.g. '654412'). Obtain this from the prediction_market_screener tool.",
+        "maxLength": 100,
+        "minLength": 1,
+        "type": "string"
+      },
+      "orderBy": {
+        "anyOf": [
+          {
+            "type": "string"
+          },
+          {
+            "type": "null"
+          }
+        ],
+        "default": null,
+        "description": "Optional sort field. Common fields: positionSize, unrealizedPnlUsd, avgEntryPrice."
+      },
+      "orderByDirection": {
+        "default": "desc",
+        "description": "Sort direction when orderBy is provided.",
+        "enum": [
+          "asc",
+          "desc",
+          "ASC",
+          "DESC"
+        ],
+        "type": "string"
+      },
+      "page": {
+        "default": 1,
+        "description": "Page number for paginated results.",
+        "minimum": 1,
+        "type": "integer"
+      }
+    },
+    "required": [
+      "marketId"
+    ],
+    "type": "object"
+  }
+]
  3. Added

TDQS

A4.5/5.0
Behavior4/5

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

The annotations declare readOnlyHint=true and destructiveHint=false, and the description does not contradict them. It adds behavioral context such as: positions are share balances not USD notional, Position Value USD is marked value not payout, and output summary is based only on shown rows. This enriches the read-only nature but does not mention pagination specifics or rate limits, which is acceptable given the annotation coverage.

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 well-structured with purposeful sections labeled 'Key fields' and 'Pitfalls' and a 'Prerequisites' note. Every bullet adds value, front-loading the most critical interpretations and cautions. No redundant sentences; each provides operational guidance.

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 (nested request schema, potential ambiguity in interpreting positions and values) and the presence of an output schema, the description covers the critical pitfalls and prerequisites that an agent needs to avoid misinterpretation. It also references related tools for lookup, completing the context. Combined with the output schema, this is adequate for correct invocation.

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?

The input schema has one parameter 'request' with nested properties, and the schema description coverage is 0% (schema properties have their own descriptions but not summarized in the tool description). The tool description does not explain the parameters beyond referencing marketId in prerequisites admissions. For example, it doesn't clarify that marketId is required in the nested schema. With 0% coverage, the description should compensate, but it partially does by mentioning the prerequisite. It lacks detail on orderBy options, which are partially self-explanatory from enums, but the description doesn't add meaning beyond schema. Score 3 as baseline for low coverage with minimal compensation.

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 states a specific verb ('finding'), a specific resource ('top holders for a Polymarket market'), and clearly distinguishes it from siblings. It names a prerequisite tool and includes usage notes, making the purpose unmistakable despite the terse title. It is clear and specific, differentiating from other prediction_market tools.

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?

Explicitly states a prerequisite: if marketId is unknown, call prediction_market_lookup first. It also warns against over-interpreting data (e.g., not labeling positions as smart money without Nansen support), which helps the agent avoid misuse. The description effectively guides correct usage and alternatives.

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