Loading ToolBench
Track top 50 Hyperliquid trader positions by PnL -- direction, size, leverage, entry price, unrealized PnL.
Single tool 'hyperliquid_track_whale_positions' has a well-structured description (280+ chars) explaining WHAT it does, WHEN to use it, and what it returns. Input schema is present with proper type definition (string, optional). However, the parameter description is minimal ('Filter by coin symbol...'), and the output schema is documented only in prose within the description rather than as a formal JSON Schema. The tool lacks error handling guidance, recovery hints, and does not declare idempotency or destructiveness. No tool annotations present. Naming is clear and verb-forward ('track'). Overall definition quality is above-average for a single-tool server but falls short of A-grade due to missing formal output schema and error patterns.
Use this when you need to see what the top Hyperliquid traders are doing. Returns aggregated positions of the top 50 traders ranked by PnL with full position details. 1. positions: array of whale positions across all coins 2. Each position contains: coin, direction (long/short), sizeUsd, entryPrice, markPrice, unrealizedPnl, leverage, traderAddress 3. summary: aggregated stats -- totalLongUsd, totalShortUsd, netBias (bullish/bearish/neutral) 4. topTraderCount: number of traders analyzed 5. timestamp: data freshness timestamp Example output: {"positions":[{"coin":"BTC","direction":"long","sizeUsd":4500000,"entryPrice":66800,"markPrice":67450,"unrealizedPnl":145000,"leverage":5.2}],"summary":{"totalLongUsd":89000000,"totalShortUsd":42000000,"netBias":"bullish"},"topTraderCount":50} Use this BEFORE taking directional trades to see whale consensus. Essential for copy-trading signals, sentiment analysis, and contrarian setups on Hyperliquid. Do NOT use for order book data -- use hyperliquid_get_market_data. Do NOT use for vault performance -- use hyperliquid_get_vault_data. Do NOT use for Solana tokens -- use solana_scan_new_tokens.
Output schema not formally documented in JSON Schema format. Description includes prose example but no structured schema definition for positions array, summary object, or timestamp field.
Parameter 'coin' description is minimal (18 chars). Does not specify format constraints, valid coin symbols, or what happens if an invalid coin is passed.
No error handling guidance. Tool description does not explain what happens on API failure, rate limiting, or invalid input. LLM has no recovery path.
No tool annotations (readOnlyHint, idempotentHint). Tool is read-only and idempotent but does not declare this via annotations, forcing LLM to infer from description.
Inferred effective spec: 2025-06-18+.
| Scored | Grade | Overall | Spec posture | Rubric |
|---|---|---|---|---|
| 2026-09-23 | C | 64 | 2025-06-18+ | v2 |
Description includes example output values (BTC, ETH, SOL) which LLMs may reuse literally. Should use enum constraint or format specification instead.