Skip to main content
Glama
Futuur MCP

Futuur MCP

Official
by futuur

Simulate an order

get_bet_simulation
Read-only

Preview a buy or sell on a Futuur market without placing an order: estimate cost or proceeds, average price, immediate fill, and shares that would rest on the book.

Instructions

Previews a buy or sell on one market without placing anything. It reads the public order book and walks it the way the matching engine would, returning the estimated cost (or proceeds), average price, how many shares would fill immediately, and how many would rest on the book. This is an estimate: the book can change before a real order is placed, and your balance and holdings are not checked. Call it before place_bet and show the numbers to the user; order in the result holds the exact arguments to give place_bet.

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": {
      "market": "<market>",
      "position": "<position>",
      "currency": "<currency>"
    },
    "name": "get_bet_simulation"
  }
}

Input Schema

NameRequiredDescriptionDefault
sideNo`bid` (default) previews buying shares; `ask` previews selling shares you hold. To buy Yes use bid with position long; to buy No use bid with position short.bid
priceNoLimit price per share, in whole cents between 0.01 and 0.99. A bid only fills at this price or lower, an ask at this price or higher. Omit for a market order that takes the best prices available.
amountNoMoney to spend, in `currency`. Only for side bid (buying). The simulation works out how many shares that buys at today's prices. Give either `shares` or `amount`.
marketYesMarket (outcome) id: the `id` of an entry in an event's `markets` list. This is not the event id.
sharesNoNumber of shares to buy or sell, at most 2 decimals. Give either `shares` or `amount`.
currencyYes`OOM` is play money. `USDC`, `USDT` and `USD` are real money and only work on events whose available_currencies include them.
positionYes`long` is the Yes side of the market (pays 1 if the outcome happens); `short` is the No side (pays 1 if it does not). Shares of each position trade in their own order book.
time_in_forceNo`gtc` (default): the part that cannot fill now rests on the book. `ioc`: the part that cannot fill now is cancelled; requires `price`.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv2.0.1

TDQS

A4.5/5.0
Behavior4/5

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

Annotations already declare readOnlyHint=true and openWorldHint=true, so the safety profile is covered; the description still adds real substance by explaining that it reads the public order book and walks it like the matching engine, and that results are estimates because the book can move. It stops short of describing rate limits or what happens on an empty book, so it is strong rather than exhaustive.

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

Conciseness5/5

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

Three sentences, front-loaded with the core action, then the returned quantities, then the estimate caveat and next step. No restatement of the title, no filler, and the most decision-relevant clause ("without placing anything") comes first.

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 no output schema, the description carries the return-value burden and does so: estimated cost or proceeds, average price, immediately filled shares and resting shares, plus the machine-readable `order` field that feeds place_bet. For an 8-parameter simulation tool that is enough to call and consume it correctly.

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 description coverage is 100% and the schema already spells out side/position semantics, price bands, amount-vs-shares exclusivity and time_in_force. The description adds no parameter-level meaning beyond a general buy-or-sell framing, so this sits at the baseline the schema earns.

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?

Opens with a specific verb and resource: "Previews a buy or sell on one market without placing anything." The phrase "without placing anything" immediately separates it from place_bet, so an agent can route correctly without reading either 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 an explicit call site ("Call it before place_bet") and a workflow step ("show the numbers to the user"), plus a handoff instruction pointing at the `order` field in the result. It also states a boundary condition: balance and holdings are not checked, so the agent knows this preview is not a validation gate.

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