Skip to main content
Glama
Sign In

Borro

by markets.borro
OverviewDiscussionsAdmin

Prepare: fund a lend or a buy from another chain

pay_with
Read-onlyIdempotent

Unsigned transactions, on another EVM chain, that lend into Borro or buy a stock token on Robinhood Chain from what the wallet holds there: any token or the chain's own coin, on any of the chains Trustware routes from (70 and more). Trustware (trustware.io) finds the route and screens it; Borro checks the route is the one asked for (the wallet's own money, Borro's own vault, the amount, the fees) before it is returned. The route is good for about a minute: sign the approvals, then the transaction, on the source chain; the deposit lands on Robinhood Chain in the wallet's name. Then pay_with_status with the intentId. A chain or token the wallet does not hold is refused with what it holds instead.

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>",
      "chain": "<chain>",
      "token": "<token>",
      "amount": "<amount>"
    },
    "name": "pay_with"
  }
}

Input Schema

NameRequiredDescriptionDefault
goalNolend (default): into Borro's vault for the asset; buy: the stock token sent to the wallet
assetNoUSDG (the default, for a lend) or a stock on Borro by its ticker, like NVDA
chainYesThe source chain: its id ("8453") or name ("base", "ethereum", "arbitrum", "optimism", "polygon", "bnb", "avalanche")
tokenYesWhat to pay with on that chain: a symbol as the wallet holds it ("USDC", "ETH", "WETH") or the token's address; the chain's own coin as "ETH" or "native"
amountYesHow much of it, in whole units as a decimal string, like "25" or "0.01"; "all" for the whole balance
walletYesThe wallet's address (0x...); the transactions are built for it to sign, on the source chain

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 already declare readOnly/non-destructive/idempotent/openWorld, and the description corroborates them by stating nothing is signed or submitted here. Beyond that it discloses the ~1-minute route validity, the two-step signing order on the source chain, that Borro re-validates the route (wallet, vault, amount, fees) before returning it, and that unsupported chains/tokens are refused with the wallet's actual holdings.

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 key fact — these are unsigned transactions on another chain — is front-loaded, and most clauses (route lifetime, signing order, status follow-up, refusal behavior) earn their place. The single dense paragraph with multiple em-dash and colon clauses makes it harder to scan than a short bulleted flow would be.

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 6-parameter preparation tool with annotations covering the safety profile and no output schema, the description covers the operational lifecycle well, including the intentId handoff to pay_with_status. It never states the shape of the returned payload (how many transactions, what approvals come back), which is the remaining gap.

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 text adds real meaning: the source chain can be any of 70+ Trustware chains (beyond the seven listed in the schema), payment can be any token or the chain's own coin, and the goal branches into lend-versus-buy outcomes.

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?

"Unsigned transactions, on another EVM chain, that lend into Borro or buy a stock token on Robinhood Chain" names a specific output artifact and both resources, and the source-chain scoping distinguishes it from same-chain siblings like buy_with_eth or supply without opening their schemas.

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?

It gives the condition for use (the wallet holds the funds on another chain that Trustware routes from) and the follow-up flow (sign approvals, sign the transaction, then call pay_with_status with the intentId). It does not explicitly name the sibling to use when the wallet already holds funds on Robinhood Chain itself, so the exclusion is only implied.

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

All Borro 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