Skip to main content
Glama

Build: create a prediction market

build_create_prediction_market
Read-only

Open a YES/NO market. The wallet seeds it with USDC liquidity (minimum 100) and names a solver — a different address that alone resolves it and stakes 1% as a bond. Trading runs until closeTime; the solver proposes after resolveAfter.

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": {
      "wallet": "<wallet>",
      "question": "<question>",
      "sector": "<sector>",
      "closeTime": "<closeTime>",
      "resolveAfter": "<resolveAfter>",
      "solver": "<solver>",
      "liquidityUsdc": "<liquidityUsdc>"
    },
    "name": "build_create_prediction_market"
  }
}

Input Schema

NameRequiredDescriptionDefault
sectorYes
solverYesthe address that will resolve the market (not the wallet)
walletYesthe agent's wallet address — the one that will sign and send the calls
questionYesa clear YES/NO question with its resolution source and time, e.g. "Will BTC close above $100,000 on Coinbase on Dec 31, 2026 (UTC)?"
closeTimeYesISO 8601 time trading stops, e.g. 2026-12-31T00:00:00Z
resolveAfterYesISO 8601 earliest time the solver may propose the outcome (≥ closeTime)
liquidityUsdcYesUSDC liquidity to seed (minimum 100), as a decimal string, e.g. "25" or "0.5"

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 already state readOnlyHint=true and openWorldHint=true; the description adds real behavior — liquidity is seeded from the wallet, 1% is bonded by the solver, and resolution timing is bounded by resolveAfter. It never discloses what the call actually produces (e.g., unsigned transaction calls for the wallet to sign), and since no output schema exists, that missing return-side behavior is a substantive gap rather than a minor one.

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 short sentences, front-loaded with the core action, with each clause carrying distinct information (instrument type, funding, solver role, timing). No filler or redundant restatement.

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 7-parameter, all-required creation tool with no output schema, the description covers the domain model well but omits the return contract entirely — an agent does not learn whether it receives calldata, a transaction request, or a market address. That omission matters precisely because no output schema exists to compensate.

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 86%, so the schema already documents nearly every parameter, including that solver must not be the wallet and that resolveAfter ≥ closeTime. The description adds marginal meaning by tying closeTime and resolveAfter to the lifecycle (trading ends vs. earliest proposal), but repeats the 100 minimum already in the liquidityUsdc description rather than extending it with format or precision guidance.

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 gives a specific verb and resource ("Open a YES/NO market") plus the distinctive mechanics — USDC liquidity seeding and a separate solver who resolves and posts a 1% bond — so an agent immediately knows what kind of object is created. It stops short of distinguishing this from siblings such as register_prediction_market, so it does not reach a 5.

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?

Useful constraints are embedded (solver must be a different address, liquidity minimum of 100, trading runs until closeTime, solver proposes after resolveAfter), which implicitly tells the agent when the call is appropriate. However, there is no explicit guidance on when to use this versus register_prediction_market or build_prediction_account, and no statement about what the caller must do next (sign and send).

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