Loading ToolBench
Model Context Protocol server for Polymarket trading - provides tools for market data queries and trading operations on Polymarket prediction markets
Server has 19 tools with consistent naming (verb_noun pattern) and descriptions present for all. However, parameter descriptions are sparse or missing entirely for most tools. Output schemas are not documented. Error handling and recovery guidance are absent. Tool composition is sound (each tool has one responsibility), but the LLM-facing documentation is incomplete.
Grant the pUSD and Conditional Token approvals required for Polymarket V2 trading and position management. Automatically approves only contracts that do not already have permission. Approvals are revocable at any time in your wallet.
Cancel all open orders for the authenticated account.
Cancel a specific order by its ID.
Get a list of all available tags for categorizing markets.
Get balance and allowance information for the authenticated account. Can check COLLATERAL or CONDITIONAL tokens.
Get detailed information about a specific event by its slug identifier. Events group multiple related markets.
Parameter descriptions missing or incomplete. Most tools have parameters (e.g., 'limit', 'offset', 'tokenId') with no description text visible in the schema. Rubric requires every parameter to have a description explaining what it controls.
Output schemas not documented. No tool includes a description of what fields the response contains, their types, or how to use them in downstream calls. LLMs cannot plan multi-step operations without knowing response structure.
Inferred effective spec: <=2025-11-25.
| Scored | Grade | Overall | Spec posture | Rubric |
|---|---|---|---|---|
| 2026-09-23 | D | 55 | <=2025-11-25 | v2 |
Get detailed information about a specific market by its slug identifier
Get markets filtered by a specific tag ID
Get all open orders for the authenticated account
Get details of a specific order by its ID
Get the order book (bids and asks) for a specific market token
Get all positions (holdings) for the authenticated account
Get trade history for the authenticated account with optional filtering
List active markets with pagination support
Place a market order (FOK or FAK) on Polymarket with automatic market parameter detection
Place a new limit order on Polymarket with automatic market parameter detection
Redeem resolved market positions to claim winnings from markets that have been resolved
Search markets, events, and profiles using a query string
Update balance and allowance for collateral or conditional tokens
No error handling or recovery guidance. Tools lack descriptions of what errors can occur, how to interpret them, or what the LLM should do next (retry, ask user, try alternative tool). Rubric requires error responses to guide the agent.
Destructive operations lack confirmation or dry-run support. Tools like cancel_order, cancel_all_orders, redeem_positions, and approve_allowances modify state but have no confirmation step or dry-run mode. Agents can make irreversible mistakes.
Numeric parameters lack bounds. Tools like list_active_markets (limit, offset) and place_order (price, size) accept numbers with no documented min/max. LLMs can pass absurd values (negative sizes, prices > 1) that break the API.