Skip to main content
Glama

AINDEX

Hyperliquid outcome markets

hyperliquid_outcomes
Read-only

Hyperliquid's outcome markets (HIP-4, tradable by AINDEX agents): price binaries and bands on BTC, ETH, SOL, HYPE and stock perps (daily and 15-minute ones), touches, sports, rate decisions and IPOs, each side's price from 0 to 1 (a winning share pays $1) and the day's volume; for a price market its terms (the perp it settles on, the level, when it ends). Filter with q words, underlying (BTC) and hours (ending within). With instrument (hyperliquid:#) it prices that side against its perp: a fair chance from the perp's volatility, the edge against the book, and the perp size that hedges a holding (shares, default 100). A model, not a promise.

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": "hyperliquid_outcomes"
  }
}

Input Schema

NameRequiredDescriptionDefault
qNo
hoursNo
limitNo
sharesNo
volPctNo
instrumentNo
underlyingNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A3.5/5.0
Behavior3/5

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

Annotations only declare read-only and open-world, so the description must carry most of the behavioural load, and it does add one substantive caveat: the valuation is 'A model, not a promise,' warning that the fair-chance figure is an estimate. It also clarifies the payout semantics ($1 per winning share) and the shares default of 100. It says nothing about the limit cap, result ordering, or what happens when instrument is combined with filters.

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

Conciseness3/5

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

The core identification is front-loaded and no sentence is pure filler, but everything is crammed into one long paragraph with chained parentheticals ('(the perp it settles on, the level, when it ends)', '(shares, default 100)'), making the two operating modes hard to scan. Splitting list-mode and pricing-mode into separate sentences would have cost nothing and gained clarity.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness3/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a seven-parameter, zero-coverage, no-output-schema tool, the description covers the return shape inline (side prices, volume, contract terms) and the two invocation patterns, which is more than most. But the omission of limit and volPct, plus no statement of ordering or result size, leaves gaps an agent would hit on first call.

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 0%, so the description is the only documentation, and it explains five of seven parameters: q as free-text words, underlying as a ticker like BTC, hours as an 'ending within' window, instrument in the hyperliquid:#<id> form, and shares with a default of 100. Two parameters, limit and volPct, are never mentioned, leaving their ranges and effect entirely undocumented.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description names a specific resource (Hyperliquid HIP-4 outcome markets) and enumerates what it returns: both sides' prices in 0-1 with a $1 payout on the winning share, day volume, and contract terms such as the settling perp and expiry level. It also exposes two distinct modes: filter/list and per-instrument pricing. It stops short of naming a sibling to distinguish itself from, so it lands at 4 rather than 5.

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 maps parameters to modes: 'Filter with q words, underlying (BTC) and hours (ending within)' versus 'With instrument (hyperliquid:#<id>) it prices that side against its perp.' That tells an agent which input combination selects which behaviour. What's absent is a 'when not to use this' clause or a named alternative for related Hyperliquid data.

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.

Resources