Skip to main content
Glama
Sign In

Vectorial Data Terminal: Hyperliquid, Polymarket & yield for AI agents

by com.vectorialdata
OverviewDiscussionsAdmin

propose_live_order

Connected AI apps with the 'live' permission: PROPOSE a real-money order on the person's Terminal account. Nothing is sent: the person gets a notification on their devices and approves it in the Terminal (approve_url, expires in 15 minutes), then it goes through the same path as their trade ticket, with the same fees and checks. Always give the person approve_url and wait; then call get_live_proposal. Actions: open (market — fills up to 5% from the price at approval — or limit with stop_loss, within 5% of the market if it crosses; stop_loss + take_profit go together as one bracket; leverage required), close (a fraction or all of a position), protect (stop and/or take profit on an open position), cancel (an open order by order_id from get_live_account). Your agent's limits apply (max_order_notional_usd, asset_allowlist).

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": {
      "action": "<action>",
      "coin": "<coin>"
    },
    "name": "propose_live_order"
  }
}

Input Schema

NameRequiredDescriptionDefault
coinYesMarket name exactly as in list_markets or get_live_account (e.g. BTC, ETH, xyz:TSLA)
noteNoWhy you propose it, in one or two sentences; the person sees it on the approval screen
sideNoopen only: long or short
actionYesopen a position, close (part of) one, protect one with stop/take profit, or cancel an open order
fractionNoclose only: share of the position to close, 0–1 (default 1 = all)
leverageNoopen: REQUIRED, leverage 1–100 within the market's maximum (the person sees it before approving)
order_idNocancel only: the order_id from get_live_account.open_orders
size_usdNoopen only: position size in USD (minimum $10); units are computed at approval with the price then
stop_lossNoopen (bracket, required for limit) or protect: stop-loss trigger price
order_typeNoopen only: market (default) or limit (needs limit_price and stop_loss)
limit_priceNoopen with order_type limit: the entry price
take_profitNoopen (together with stop_loss) or protect: take-profit trigger price

Schema Changelog

Changes observed during successful MCP inspections.

  1. Added

TDQS

A4.5/5.0
Behavior5/5

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

Annotations only say it's a non-readonly, non-idempotent, open-world call; the description adds substantial behavior beyond that - nothing is sent until human approval, the approve_url expires in 15 minutes, approval routes through the normal trade ticket with identical fees and checks, and agent-level limits (max_order_notional_usd, asset_allowlist) apply. Market-order slippage bounds (5% from approval price) and the limit-crossing rule are disclosed too.

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?

Front-loads the core concept and the critical human-approval loop before the dense action list. The action breakdown uses em-dash-packed clauses that are efficient but read as cramped; still, every sentence carries operational information.

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?

For a 12-parameter, no-output-schema, human-in-the-loop tool, the description covers the approval lifecycle, follow-up call, limits, and per-action requirements. The only gap is what the proposal response contains beyond approve_url (e.g., a proposal identifier for get_live_proposal), which the agent must infer.

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 100%, so the baseline is 3, but the description genuinely adds constraint semantics the schema only hints at: leverage is required for open, stop_loss and take_profit form a single bracket, limit orders need stop_loss, and order_id must come from get_live_account. Minor fields like note and size_usd semantics rest entirely on the schema.

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 verb and resource - 'PROPOSE a real-money order on the person's Terminal account' - and immediately clarifies that nothing is actually sent until human approval. The four supported actions (open, close, protect, cancel) are enumerated, so an agent can tell this apart from cancel_live_proposal, get_live_proposal, and the raw order-placement siblings.

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

Usage Guidelines4/5

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

Gives a clear precondition ('Connected AI apps with the live permission') and an explicit follow-up protocol: always hand over approve_url, wait, then call get_live_proposal. It does not directly contrast with place_order/submit_order/submit_intent, which an agent would need to choose among, so it falls short of full when-not/alternative guidance.

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

All Vectorial Data Terminal: Hyperliquid, Polymarket & yield for AI agents toolsInspect
Try in Browser
One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources