Skip to main content
Glama

Ironflow: Hyperliquid data

HIP-4 outcome markets overview

get_outcome_markets
Read-only

Hyperliquid HIP-4 outcome markets (prediction markets on sports, central bank decisions, IPOs and daily BTC price contracts) over the last 4 hours, 1 day or 1 week: traded volume (each trade counted once), fills, wallets and active markets, plus the most traded outcomes with their last traded price (the implied probability, 0 to 1) and last-24-hour traded volume. Each outcome has a Yes and a No side whose prices sum to 1. For one outcome's trades or candles pass its symbol to get_recent_trades or get_candles; settled outcomes stay queryable. For per-wallet outcome activity use run_query on hl.wallet_daily with market_class = 'prediction'.

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "get_outcome_markets"
  }
}

Input Schema

NameRequiredDescriptionDefault
limitNoNumber of outcomes to return, most traded first (1-200, default 20)
windowNoLookback window for the totals (default 1d)

Output Schema

NameRequiredDescriptionDefault
noticeNoPresent when the API added a note: how a market name was read, that data starts later than asked because of the history window, or a next step such as a free key
volume_usdNoTraded volume in USD over the window, each trade counted once
computed_atNoWhen the summary was computed, Unix seconds
fills_totalNoFill rows over the window, both sides of each trade plus settlements, splits and merges
top_marketsNoMost traded outcome sides, highest 24h traded volume first
window_hoursNoWindow of the totals, in hours
wallets_totalNoWallets with any fill over the window, including wallets that only settled, split or merged
markets_activeNoOutcome sides with a fill in the window
notional_totalNoNot traded volume: USD over every fill row, both sides of each trade plus settlements, splits and merges. Use volume_usd

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed13 schema fields changed
    • changedOutput schema / properties / fills_total / description
      Previous value: -"Fills over the window"New value: +"Fill rows over the window, both sides of each trade plus settlements, splits and merges"
    • changedOutput schema / properties / markets_active / description
      Previous value: -"Outcome markets listed now"New value: +"Outcome sides with a fill in the window"
    • changedOutput schema / properties / notional_total / description
      Previous value: -"Volume in USD over the window"New value: +"Not traded volume: USD over every fill row, both sides of each trade plus settlements, splits and merges. Use volume_usd"
    • changedOutput schema / properties / top_markets / description
      Previous value: -"Most traded outcomes, highest 24h volume first"New value: +"Most traded outcome sides, highest 24h traded volume first"
    • changedOutput schema / properties / top_markets / items / properties / fills_24h / description
      Previous value: -"Fills in the last 24 hours"New value: +"Fill rows in the last 24 hours"
    • changedOutput schema / properties / top_markets / items / properties / last_fill_ms / description
      Previous value: -"Last fill, Unix milliseconds"New value: +"Last fill of any kind, Unix milliseconds"
    • changedOutput schema / properties / top_markets / items / properties / last_price / description
      Previous value: -"Last traded price, the implied probability (0 to 1)"New value: +"Last traded price, the implied probability (0 to 1); null when this side had no trade in 24 hours"
    • addedOutput schema / properties / top_markets / items / properties / last_trade_ms
      Added value: +{
      +  "description": "Last trade, Unix milliseconds"
      +}
    • addedOutput schema / properties / top_markets / items / properties / last_trade_price
      Added value: +{
      +  "description": "Same as last_price, 0 when this side had no trade in 24 hours"
      +}
    • changedOutput schema / properties / top_markets / items / properties / notional_24h / description
      Previous value: -"Volume in USD in the last 24 hours"New value: +"Not traded volume: USD over every fill row of this side in 24 hours. Use volume_24h"
    • addedOutput schema / properties / top_markets / items / properties / volume_24h
      Added value: +{
      +  "description": "Traded volume in USD on this side in the last 24 hours, each trade once. The two sides of an outcome share one book: add both for the outcome's volume"
      +}
    • addedOutput schema / properties / volume_usd
      Added value: +{
      +  "description": "Traded volume in USD over the window, each trade counted once"
      +}
    • changedOutput schema / properties / wallets_total / description
      Previous value: -"Wallets that traded over the window"New value: +"Wallets with any fill over the window, including wallets that only settled, split or merged"
  2. Added

TDQS

A4.2/5.0
Behavior4/5

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

Annotations already establish readOnlyHint=true and openWorldHint=true, so the bar is lower; the description still contributes non-obvious semantics: volume counts each trade once, prices are implied probabilities on a 0-1 scale with Yes/No sides summing to 1, and settled outcomes remain queryable. These clarify interpretation rather than restating the safety profile. Pagination and ordering beyond the schema's 'most traded first' are not discussed, keeping it short of a 5.

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?

The core scope and payload come first, followed by interpretation notes and then sibling routing, which is the right order. The opening sentence is long and parenthetical-heavy, but each clause carries real information rather than filler.

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?

With an output schema present, the description needn't enumerate return fields, and it instead covers what the schema cannot: the market universe, volume deduplication, implied-probability interpretation, and where to go for per-outcome or per-wallet detail. For a 2-parameter read-only analytics tool, nothing an agent needs to call it correctly is missing.

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 coverage is 100%, so both parameters (limit 1-200 default 20, window enum 4h/1d/1w default 1d) are fully documented in the schema. The description only mentions the three window values in prose for framing, without adding syntax, ordering, or edge-case meaning beyond the schema. Baseline 3 applies.

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 names a specific data product (Hyperliquid HIP-4 outcome/prediction markets) and enumerates exactly what the response contains: traded volume, fills, wallets, active markets, and top outcomes with last price as implied probability plus 24h volume. It also defines the domain (sports, central bank decisions, IPOs, daily BTC contracts), which separates it from spot/market snapshot 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?

It explicitly routes two adjacent needs elsewhere: per-outcome trades/candles go to get_recent_trades or get_candles by symbol, and per-wallet outcome activity goes to run_query on hl.wallet_daily with market_class = 'prediction'. That is concrete alternative-selection guidance. It does not address when to prefer this over get_markets_snapshot or list_markets, which is the remaining gap.

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

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.