Bitquery: Crypto & Blockchain Data

Hyperliquid Trader Summary

hyperliquid_trader_summary

Read-only

PERIOD SCORECARD of ONE Hyperliquid account — realized PnL, funding, fees, net result, volume, fill count, win rate, maker/taker split, markets traded — in total or per market. Use for "how is this wallet doing", "is this trader profitable", comparing wallets. NOT the fill list (hyperliquid_trader_fills), NOT open positions (hyperliquid_trader_positions), NOT a ranking across wallets (hyperliquid_top_traders).

Net_Pnl_Usd = Realized_Pnl_Usd (closes, incl. liquidations) + Funding_Usd (signed; paid funding is negative) - Fees_Usd (USDC fees; a maker rebate lowers them). Unrealized PnL of open positions is NOT included — read hyperliquid_trader_positions for it. Win_Rate_Pct = share of closing fills with positive realized PnL. Volume_Usd counts the account's own fills once. Taker_Share_Pct, Twap_Share_Pct, Agent_Signed_Pct (fills signed by an API wallet), Liquidations and Liquidated_Usd (only the times the account itself was liquidated; a fill that took over a liquidated position counts in Fills and Volume_Usd, not here). group_by = market splits the same columns per market; there a live outcome (prediction) market also carries Headline, Outcome and Outcome_Side (its names, from the newest state snapshot; NULL otherwise). hours up to 720 (30 days); most fields come from 5-minute roll-ups, so a window is honoured at 5-minute granularity.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "trader": "<trader>"
    },
    "name": "hyperliquid_trader_summary"
  }
}

Input Schema

Name	Required	Description	Default
`hours`	No	Window in hours, 1..720. Default 168 (7 days).
`format`	No	Shape of the returned data. "rows" (the default) returns one item per row. "columnar" returns a single item, {"columns":[...],"rows":[[value,...],...]}, naming the columns once and listing each row's values in that order; it is more compact for large results and carries the same values.	rows
`trader`	Yes	Account, 0x-hex (40 hex chars, case-insensitive). Required.
`group_by`	No	'' (default) = one total row \| market = one row per market.

Schema Changelog

Changes observed during successful MCP inspections.

Changed1 schema field changedOct 28, 2026

addedInput schema / properties / format

Added value: +{
+  "default": "rows",
+  "description": "Shape of the returned data. \"rows\" (the default) returns one item per row. \"columnar\" returns a single item, {\"columns\":[...],\"rows\":[[value,...],...]}, naming the columns once and listing each row's values in that order; it is more compact for large results and carries the same values.",
+  "type": "string"
+}

First observedOct 7, 2026

TDQS

A4.8/5.0

Behavior5/5

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

Beyond readOnlyHint/destructiveHint, it discloses metric derivations (Net_Pnl = Realized + Funding - Fees, signed funding, maker rebate treatment), that unrealized PnL is excluded, that data comes from 5-minute roll-ups so windows are honored at 5-minute granularity, liquidation-exclusion semantics, and NULL behavior on prediction-market fields. This is unusually rich behavioral context.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Purpose and sibling exclusions are front-loaded and every sentence carries substantive metric definition. However, the dense run-on parentheticals make it harder to parse than necessary and some field-level detail could be tightened.

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?

No output schema exists, yet the description defines the returned metrics and their computation, the per-market variant, the prediction-market edge case, and window granularity. An agent knows what it will get back and how to interpret it.

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

Parameters4/5

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

Schema coverage is 100%, so the baseline is 3, but the description adds real meaning: group_by=market splits the same columns per market and adds Headline/Outcome/Outcome_Side for live prediction markets, and hours is capped at 720 with 5-minute granularity. It stops short of covering the format parameter's row/columnar tradeoff, which lives only in the schema.

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?

States a specific resource and scope ("PERIOD SCORECARD of ONE Hyperliquid account") with an enumerated metric set, and explicitly names the three sibling tools it is not. An agent can distinguish it from hyperliquid_trader_fills, hyperliquid_trader_positions, and hyperliquid_top_traders without opening a schema.

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?

Gives concrete triggering questions ("how is this wallet doing", "is this trader profitable", comparing wallets) plus explicit exclusions mapping to the correct alternatives, and redirects to hyperliquid_trader_positions for unrealized PnL. When-to-use, when-not, and alternatives are all present.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

All Bitquery: Crypto & Blockchain Data tools Inspect

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.