Skip to main content
Glama
Sign In
GDEX Trading

GDEX Trading

by GemachDAO
OverviewSchemaSourceRelated ServersDiscussionsAdmin
TypeScript
Remote

gdex_make_challenge

Read-only

Convert a verified trade close or packaged scenario into a practice challenge another agent can play; preview the exact message first, then export only after user confirmation.

Instructions

Turn a verified full close (closeId from gdex_replay_trade) or a packaged scenario (scenarioId) into a practice challenge another agent can play. First call returns a PREVIEW of the exact message: show it to the user. Only after they confirm, call again with confirmExport: true and the exportToken. The capsule names a synthetic practice scenario; it never contains wallet/account ids, balances, size, fills, order ids, exact times or P&L. Nothing is sent anywhere; the user copies the message.

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": "gdex_make_challenge"
  }
}

Input Schema

NameRequiredDescriptionDefault
closeIdNoA full close from gdex_replay_trade
accountRefNo
scenarioIdNoStandalone practice scenario: eth-short-target-vs-stop-01, btc-long-target-vs-stop-01
exportTokenNoFrom the preview
confirmExportNoTrue only after the user approved the previewed message
includeInviteNoAdd the user's existing GDEX invite link, with a disclosure. Off by default; only if the user asks.
includeSenderPlanNoAdd the trade's TP/SL distances (rounded %) as the plan to compare against. Off by default.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Addedv5.4.1

TDQS

A4.9/5.0
Behavior5/5

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

Goes well beyond the readOnlyHint/openWorldHint annotations: it enumerates exactly what the capsule excludes (wallet/account ids, balances, size, fills, order ids, exact times, P&L) and states that nothing is transmitted and the user copies the message. That privacy profile and the preview-then-confirm gating are the behaviors an agent most needs to know before calling.

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?

Roughly four sentences, front-loaded with the transformation and sources, then the confirm flow, then the privacy guarantee. The long enumeration of excluded fields is dense but each item is load-bearing for the privacy claim.

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 and seven optional parameters, the description still tells the agent what the first response is (a preview of the exact message), what the final artifact contains, and that it never leaves the machine. Nothing needed to call it correctly in sequence is missing.

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 already 86%, so the baseline is 3; the description still adds provenance for closeId/scenarioId, the origin of exportToken ('From the preview'), and the comparison purpose of includeSenderPlan. The one gap is accountRef, which is undocumented in both the schema and the description.

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?

Names a specific verb (turn ... into a practice challenge) plus both accepted resource sources (closeId from gdex_replay_trade, or scenarioId for a packaged scenario), and states the output is a message another agent can play. An agent can distinguish this from gdex_run_challenge or gdex_invite purely from the description.

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 two-step protocol: first call returns a PREVIEW that must be shown to the user, and the second call is allowed only after confirmation, with confirmExport: true plus the exportToken. It also gates the optional includeInvite behind an explicit user request ('Off by default; only if the user asks'), leaving little to inference.

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

Deploy Server

Other Tools