Skip to main content
Glama

Nansen

by io.github.nansen-ai
OverviewDiscussionsAdmin

Checking prediction market orderbook

prediction_market_orderbook
Read-only

Live orderbook for a Polymarket market.

When to use:

  • Bid/ask depth, liquidity, and yes-share / no-share order structure.

Key fields:

  • Order Size is share quantity, not USD. Do not describe share size as dollar depth unless you calculate shares × price.

Yes/No price relationship:

  • Yes and No are complementary (Yes + No ≈ $1). A No bid at price $X means willingness to buy No when Yes is near $(1−X).

  • A cluster of No bids at low prices (e.g. $0.20) is resistance for Yes rallying to ~$0.80, NOT a support floor for the current Yes price.

  • When comparing OHLCV odds against orderbook depth, convert No-side prices to Yes-equivalent (1 − No price) before drawing divergence conclusions.

Pitfalls:

  • Do not treat raw no-share prices as bearish yes-share odds — prefer prediction_market_ohlcv for current odds / implied probability.

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

A4.7/5.0
Behavior5/5

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

Beyond the readOnly/openWorld annotations, the description adds critical behavioral nuance: order size is share quantity not USD, Yes and No are complementary, No bids act as resistance to Yes rallies, and No-side prices must be converted to Yes-equivalent before comparing with OHLCV. These guardrails materially change how an agent interprets results.

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 long but well-structured with bold section headers, and each bullet provides distinct, non-redundant guidance. No sentence is filler; the Yes/No relationship and pitfall details earn their space.

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 output schema exists, return format does not need to be described. The description covers when to use, how to source the required `marketId`, how to interpret values, and which sibling to prefer, making it complete 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?

Schema description coverage is 0%, and the description does not explain the `request` object or `page` parameter, though the schema itself already documents `marketId` and `page` properties. It does add the useful prerequisite 'If `marketId` is unknown, call `prediction_market_lookup` first', but this conflicts slightly with the schema's `marketId` description which says to obtain it from `prediction_market_screener`.

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 resource ('Live orderbook for a Polymarket market') and enumerates its intended outputs: bid/ask depth, liquidity, and yes-share/no-share order structure. It also implicitly distinguishes itself from the sibling `prediction_market_ohlcv` by pointing to that tool for current odds and implied probability.

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?

It has an explicit 'When to use' bullet, a 'Pitfalls' section that explicitly routes to `prediction_market_ohlcv` for current odds, and a 'Prerequisites' telling the agent to call `prediction_market_lookup` if `marketId` is unknown. This leaves no ambiguity about when to pick this tool over siblings.

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