Skip to main content
Glama
Sign In

Borro

by markets.borro
OverviewDiscussionsAdmin

Check a counterparty's repayment record

counterparty_check
Read-onlyIdempotent

Another lender's repayment record of an agent or a wallet: Priors' record on Robinhood Chain (loans repaid and their USDG, loans open, any default, its Priors Score v2 and rung), read live from Priors' check API and given in Borro's own words. agent: an ERC-8004 agent id; address: a wallet (an agent's, a payee's, an x402 payTo), which finds the agents it owns or pays for (at most 3 shown, best rung ahead); exactly one. It is Priors' record, not Borro's, and Borro does not vouch for it: check_on_chain says how to read Priors' score from the ERC-8004 registry yourself. verdict: no record, no repayments yet, repaid or defaulted. proven is true when a listed agent has a published Priors Score v2 at rung 2 or more (proven: three or more backed repayments over 14 days or more, none late), no default and is not frozen; anything missing counts as not proven. credit_open, credit_line, credit_guardrails, credit_pay, credit_bill, hold_open and account_open show the same record as agent_record or payee_record when Priors answers within 2.5 seconds.

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": "counterparty_check"
  }
}

Input Schema

NameRequiredDescriptionDefault
agentNoAn ERC-8004 agent id, like "462"
addressNoA wallet: 0x and 40 hex characters

Schema Changelog

Changes observed during successful MCP inspections.

  1. Added

TDQS

A4.2/5.0
Behavior4/5

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

Annotations already cover read-only/idempotent/no-destroy safety, and the description adds real context beyond them: data is read live from Priors' API under a 2.5-second answer window, Borro does not vouch for it, and the verdict/proven semantics are spelled out. It stops short of describing pagination or failure behavior when Priors is unavailable.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness3/5

Is the description appropriately sized, front-loaded, and free of redundancy?

A single dense run-on paragraph mixing purpose, parameter rules, verdict definitions, and fallback behavior. The most decision-relevant facts (what it fetches, agent-or-address) are buried mid-sentence, and the credit_* enumeration at the end is hard to parse.

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?

No output schema exists, and the description compensates by defining verdict values, the proven condition (three-plus backed repayments over 14+ days, no default, not frozen), and the 2.5-second timeout for sibling mirrors. Complete enough to call correctly, though the exact response object shape remains implicit.

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% (baseline 3), and the description adds meaning beyond it: the mutual exclusivity ('exactly one'), that an address resolves to agents it owns or pays for with at most 3 shown, best rung first, and that agent is an ERC-8004 id. This materially improves on the terse schema strings.

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: reading another lender's (Priors') repayment record for an agent or wallet, including the fields returned (repayments, open loans, default, Score v2, rung). It is clearly distinguishable from siblings like credit_line or account_status because it explicitly frames itself as third-party record lookup.

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?

Says 'exactly one' of agent/address and enumerates when to pass an address (an agent's, a payee's, an x402 payTo) vs an agent id. It also points to check_on_chain as the alternative for reading the score directly from the registry. No explicit when-not-to-use for the credit_* siblings beyond a passing mention.

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