Skip to main content
Glama

Buy at price

buy_at_price

Plan a buy of a stock token on Robinhood Chain for wallet that waits for a price: when the pool price goes trigger below or above price_usd, keyfo prepares a buy of usd or eth and a sign link. Nothing is bought or signed now. The plan starts after the wallet’s owner confirms it at https://keyfo.xyz/app. The price is the pool’s 5-minute median from at least 5 samples, and the level must hold for about 3 minutes. Only pools with at least $250000 of depth qualify, and no buy is prepared if the route costs more than 3% above the median. The owner then has 6 hours to sign. It is not a limit order: the buy goes at the market price when it is signed. One time by default; with repeat, it waits again after each buy. Limits as for scheduled buys: 5 plans per wallet, $500 per buy, $1000 a week.

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>",
      "wallet": "<wallet>",
      "trigger": "<trigger>",
      "price_usd": "<price_usd>"
    },
    "name": "buy_at_price"
  }
}

Input Schema

NameRequiredDescriptionDefault
ethNoETH to spend on the buy. Give usd or eth, not both.
usdNoDollars of ETH to spend on the buy, at the ETH price when it is prepared. Up to 500.
tokenYesTicker, like NVDA, or the token address.
repeatNotrue waits for the price again after each buy. Default: false, one buy.
walletYesThe wallet that buys and signs. Its owner confirms the plan at https://keyfo.xyz/app.
triggerYesbelow or above: buy when the pool price drops below or rises above price_usd.
price_usdYesThe price in dollars that starts the buy, like 160.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.6/5.0
Behavior5/5

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

With readOnlyHint=false and destructiveHint=false already declared, the description still adds substantial behavior: nothing is bought or signed now, the owner must confirm at keyfo.xyz/app, the price is a 5-minute median of at least 5 samples holding ~3 minutes, pools need $250k depth, routes costing over 3% above median abort the buy, and there is a 6-hour signing window. These are exactly the non-obvious facts an agent needs before promising a user what will happen.

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?

The lede sentence front-loads what the tool does and how it waits, and subsequent sentences layer constraints in a sensible order (price source, depth/route guards, signing window, limits). It is dense — a single block carrying many facts — but almost every clause is load-bearing; light bolding or bullets would improve scanability without cutting content.

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?

For a complex, deferred, human-in-the-loop planning tool with no output schema, the description covers timing, confirmation flow, price-quality rules, abort conditions, signing deadline, and quota limits. An agent can set correct user expectations and call the tool with the right parameters from this text alone.

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 adds meaning beyond it: `repeat` is framed behaviorally as re-arming after each buy, `trigger` as a directional crossing of price_usd, and per-buy/per-week limits ($500 per buy, $1000 a week, 5 plans per wallet) are constraints absent from the schema. It adds value without duplicating field documentation.

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?

The description uses a specific verb and resource — 'Plan a buy of a stock token on Robinhood Chain' — with the defining mechanism stated immediately: it waits for a pool price to cross a trigger. It also explicitly disclaims the nearest wrong mental model ('It is not a limit order'), so an agent can separate it from build_trade or schedule_buy without opening the schema.

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?

The conditions for use are explicit: buy when the pool price goes below or above price_usd, one-shot by default, repeated only if `repeat` is set. It also clarifies the limit-order misconception and cross-references 'Limits as for scheduled buys'. What's absent is an explicit routing statement (e.g. 'use schedule_buy instead when you want a time-based buy'), but the scenario is unambiguous.

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