Skip to main content
Glama

AINDEX

Spreads between venues

get_spreads
Read-only

Spreads between venues for the same market, as perpdexlist.com/arbitrage shows them: every symbol on two or more of Lighter RH, main Lighter and Hyperliquid (crypto, and its stock, index and commodity perps), with each venue's mark and hourly funding. funding: the highest hourly funding minus the lowest, what a short where it is highest and a long where it is lowest earn an hour on each leg before fees, and that rate held a year (not a forecast). price: the dearest mark over the cheapest. tradable: both funding legs are on venues an AINDEX agent trades now (Lighter RH, main Lighter, and Hyperliquid's own perps where the service trades there; its stock perps are read only). Sort by funding or price; only venues trading at least min_volume a day count. Whether one is worth taking (fees on both legs, how long it lasts, margin on both sides) is a judgment; an AINDEX agent puts both legs on together as one linked trade.

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_spreads"
  }
}

Input Schema

NameRequiredDescriptionDefault
sortNo
limitNo
tradableNo
minVolumeUsdNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A3.7/5.0
Behavior4/5

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

Annotations already cover the read-only and open-world profile, yet the description still adds real behavior: the data mirrors perpdexlist.com/arbitrage, coverage is limited to symbols on two or more venues, venues below min_volume are excluded from the result set, stock perps are read-only, and the annualized figure is a held rate rather than a forecast. It stops short of describing result ordering defaults or what an empty result means.

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?

Purpose is correctly front-loaded and every clause carries information, but the body is a run-on chain of semicolons with heavy jargon ("what a short where it is highest and a long where it is lowest earn an hour on each leg") that an agent must parse rather than read off. It could be restructured into short labeled definitions without losing content.

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

Completeness4/5

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

With no output schema, the description does the work of explaining the returned fields — each venue's mark and hourly funding, the funding spread, the price spread, and the tradable flag — which is exactly what an agent needs to interpret results. The missing pieces are the limit parameter's behavior and any statement of ordering/default.

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 0%, so the description must carry the load, and it defines three of four parameters: the sort dimension ("funding or price"), the tradable filter ("both funding legs are on venues an AINDEX agent trades now"), and min_volume ("only venues trading at least min_volume a day count"). The limit parameter is never mentioned, leaving its effect on the result set 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?

"Spreads between venues for the same market" names a specific resource and computation, and the description scopes it to symbols listed on two or more of Lighter RH, main Lighter and Hyperliquid. It never explicitly names a sibling to contrast with (e.g. get_lighter_markets or get_derivatives), so differentiation is left to inference.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines3/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Usage is implied rather than stated: an agent should call this when comparing funding and mark across venues for an arbitrage decision, and the description closes by noting that judging whether a spread is worth taking is the caller's job and that both legs go on as one linked trade. There is no explicit when-not or "use X instead" routing against the many sibling market tools.

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