Skip to main content
Glama

Funding pairs that paid after costs

get_net_arbs
Read-only

Funding pairs ranked by what they actually made over the last 7 days at a given size per leg: the funding each pair paid (recorded hourly, not today's rate) minus taker fees to open and close both legs (Angler's fee included) minus both order books' slippage at that size (sampled every 15 minutes on Hyperliquid, Lighter, Lighter RH, Aster, Pacifica, Phoenix and TxFlow). Pairs without a week of history or a book sample are left out. Each can be run as a funding bot on Angler's Bots page.

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_net_arbs"
  }
}

Input Schema

NameRequiredDescriptionDefault
limitNoHow many pairs, 1-25. Default 10.
size_usdNoDollars per leg. Default 10,000.
min_volume_usdNoMinimum 24h volume of the asset in USD. Default 1,000,000; 0 includes thin markets.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A3.9/5.0
Behavior4/5

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

Goes well beyond the readOnly/openWorld annotations by disclosing the cost model (taker fees both legs, Angler's fee included), slippage sampling cadence (every 15 minutes) and venue list, and history (hourly recorded funding, 7-day window). It also discloses exclusions: pairs lacking a week of history or a book sample are dropped. Only the exact return shape is left implicit.

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?

A single dense sentence that is front-loaded with the ranking metric and then layers the cost methodology. Every clause carries information, though the run-on structure and venue enumeration make it heavier to parse than necessary.

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 still conveys how results are ranked and what they represent, plus the exclusion rules that explain missing pairs. It is close to complete for a read-only analytics tool; only the concrete returned fields are unspecified.

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 the baseline is 3. The description reinforces that size is applied per leg and that slippage is computed at that size, which clarifies intent, but it says nothing about the limit or min_volume_usd parameters beyond what the schema already documents.

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 metric: funding pairs ranked by realized net earnings over the last 7 days at a given size per leg. It clearly differentiates itself from raw-rate siblings by emphasizing what was actually paid after fees and slippage, so an agent can tell it apart from find_funding_arbs or get_funding_rates.

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?

The description implies when this is useful (you want net-of-cost historical performance rather than current rates) and mentions the pairs can be run as a funding bot afterward. However, it never explicitly names an alternative tool or states a when-not-to-use condition, leaving routing to inference.

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