Skip to main content
Glama

Route a private buy order

route_order

Buys stock tokens with shielded USDG by splitting the order into random pieces sent at random times to fresh addresses, so trades do not trace back to the agent's wallet.

Instructions

Buys a stock token with shielded USDG, split into pieces of random size sent at random times inside the window. Each piece goes to its own fresh address, so the trades do not trace back to the agent's wallet. Returns at once; pieces are sent in the background (check with get_orders / get_fills). Privacy is from other readers of the chain, not from Robinhood.

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": {
      "token": "<token>",
      "usdgAmount": "<usdgAmount>"
    },
    "name": "route_order"
  }
}

Input Schema

NameRequiredDescriptionDefault
tokenYesSymbol of an allowlisted stock token, e.g. MSTK on testnet
piecesNoHow many pieces (1 to 20)
usdgAmountYesTotal USDG to spend
windowMinutesNoSpread the pieces over this many minutes
maxSlippagePercentNoWorst price accepted per piece, in percent

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.1

TDQS

A4.2/5.0
Behavior4/5

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

With no annotations, the description carries the full burden and does substantial work: it discloses asynchronous execution (returns at once, pieces sent in background), per-piece fresh addresses, randomized sizing/timing, and an honest privacy boundary. Gaps remain around the immediate return payload (order id?), failure/insufficient-balance behavior, and whether pieces can be cancelled via cancel_order.

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?

Four short sentences, front-loaded with the core action and mechanism, then async behavior, then the privacy caveat. No filler; each sentence carries information an agent needs.

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 5-parameter mutation tool with no annotations and no output schema, the description covers the essential behavior (what happens, timing, anonymity model, where to poll). It falls short on what the immediate response contains and on error/cancellation paths, which matter for a tool that fires background trades.

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 does add some meaning beyond the schema — pieces are random-sized and sent at random times inside the window, which explains the interaction between pieces and windowMinutes — but it says nothing about maxSlippagePercent or token allowlisting semantics.

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: buys a stock token with shielded USDG, split into randomized pieces across fresh addresses. It is clearly distinguishable from the sibling read tools (get_orders, get_fills) it explicitly points to for follow-up, and from cancel_order/deposit in the flow.

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 clear context for using it (private execution of a buy) and names get_orders/get_fills for checking status after the immediate return. It also sets an expectation boundary with 'Privacy is from other readers of the chain, not from Robinhood.' There is no explicit when-not-to-use guidance or mention of cancel_order for aborting in-flight pieces.

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