Skip to main content
Glama

Nansen

by io.github.nansen-ai
OverviewDiscussionsAdmin

Checking prediction market PnL leaders

prediction_market_pnl_leaderboard
Read-only

PnL leaderboard for a Polymarket market.

When to use:

  • Only for profitability claims.

Key fields:

  • Total PnL USD = redemption + unrealized value + sell proceeds − buy cost, for this market only.

  • Net Buy Cost USD is what the wallet paid for shares.

  • Net Sell Proceeds USD is what it received for shares sold before resolution.

  • Redemption Value USD is the payout collected after the market settled.

  • Unrealized Value USD is the marked value of shares still held.

  • Side Held reflects current side exposure where the API provides it.

Pitfalls:

  • The API gives no ROI, volume, or trade count here. Do not state them.

  • If PnL fields are blank, say profitability is unavailable — do not substitute top holders or position size.

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. Changed3 schema fields changed
    • removedInput schema / $defs
      Removed value: -{
-  "PredictionMarketPnlLeaderboardRequest": {
-    "description": "Request for market-level PnL leaderboard.",
-    "properties": {
-      "marketId": {
-        "description": "Numeric Polymarket market ID (e.g. '654412'). Obtain this from the prediction_market_screener tool.",
-        "maxLength": 100,
-        "minLength": 1,
-        "type": "string"
-      },
-      "page": {
-        "default": 1,
-        "description": "Page number for paginated results.",
-        "minimum": 1,
-        "type": "integer"
-      }
-    },
-    "required": [
-      "marketId"
-    ],
-    "type": "object"
-  }
-}
    • addedInput schema / additionalProperties
      Added value: +false
    • changedInput schema / properties / request / anyOf
      Previous value: -[
-  {
-    "additionalProperties": true,
-    "type": "object"
-  },
-  {
-    "$ref": "#/$defs/PredictionMarketPnlLeaderboardRequest"
-  }
-]New value: +[
+  {
+    "additionalProperties": true,
+    "type": "object"
+  },
+  {
+    "additionalProperties": false,
+    "description": "Request for market-level PnL leaderboard.",
+    "properties": {
+      "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. Added

TDQS

A4.3/5.0
Behavior5/5

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

Annotations already mark the tool as readOnly and non-destructive, but the description goes well beyond that by defining the exact PnL formula, explaining each field, and warning that ROI, volume, and trade count are not provided. It also tells the agent how to behave when PnL fields are blank, which is valuable operational guidance.

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 organized into clear, scannable sections with front-loaded purpose, definitions, pitfalls, and prerequisites. Every section adds practical value, and the bullets make the longer content easy for an agent to parse.

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?

For a tool with this complexity, the description is remarkably complete: it covers the PnL formula, field meanings, missing-data behavior, and prerequisites, while the output schema handles return shape. It falls slightly short due to the inconsistent marketId source guidance and the lack of explicit differentiation from similar PnL tools.

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

Parameters2/5

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

The top-level request parameter has 0% schema description coverage and the description does not explain the request object or the page parameter. It does note that marketId can be obtained via prediction_market_lookup, but this conflicts with the schema's instruction to get it from prediction_market_screener, and no other parameter semantics are compensated for.

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 opens with a specific definition: 'PnL leaderboard for a Polymarket market,' which names the resource and scope. It further narrows the purpose with 'Only for profitability claims' and explains the key PnL fields, making it clearly distinguishable from token- or address-level PnL siblings.

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 'When to use' section explicitly limits the tool to profitability claims, and the prerequisites section gives a concrete next step if marketId is unknown. It does not name sibling alternatives or give explicit when-not-to-use exclusions beyond profitability claims, so a small gap remains.

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