Skip to main content
Glama

Quanta Finance Deal Check

Check a deal

check_deal_fit
Read-onlyIdempotent

Check a real estate investment deal against Quanta Finance's published loan terms. Returns a verdict (fits, resize, review or does_not_work), the largest loan the published terms allow, follow-up questions and the next step. A verdict needs the property's state; without one the result is needs_state. The next step includes quoteUrl, a link that opens Quanta's quote form with the deal filled in. Each result is an estimate, not a loan approval or a commitment to lend, and starts with a notice that says so. Loans are for business purposes on non-owner-occupied investment property only.

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": "check_deal_fit"
  }
}

Input Schema

NameRequiredDescriptionDefault
arvNoAfter-repair value in USD
entityNoHow the borrower will take title
holdbackNoLoan amount held back for the rehab in USD, when stated
timelineNoWhen they need to close
ficoRangeNo
loanAmountNoTotal loan amount in USD the person asked for, if they named one
downPaymentNoCash the borrower puts toward the purchase in USD, when stated
initialLoanNoLoan amount at closing toward the purchase in USD, when stated
projectTypeNoProgram slug that fits the project
rehabBudgetNoRehab or construction budget in USD
ownerOccupiedNotrue if the borrower plans to live in the property
propertyStateNoTwo-letter US state code of the property, DC for Washington DC. A verdict needs it.
purchasePriceNoPurchase price in USD, or current value for a refinance
propertyAddressNo
rehabLoanPercentNoShare of the rehab the loan covers, as the stated percent
projectsLast3YearsNoSimilar projects completed in the last 3 years
purchaseLoanPercentNoShare of the purchase price the loan covers at closing, as the stated percent, such as 65.28

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed2 schema fields changed
    • changedInput schema / properties / loanAmount / description
      Previous value: -"Total loan amount in USD, only when the visitor asked for or stated one"New value: +"Total loan amount in USD the person asked for, if they named one"
    • changedInput schema / properties / propertyState / description
      Previous value: -"Required. Two-letter US state code of the property, DC for Washington DC. Ask the person if you do not know it; never guess."New value: +"Two-letter US state code of the property, DC for Washington DC. A verdict needs it."
  2. First observed

TDQS

A4.4/5.0
Behavior5/5

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

Annotations already declare a safe read, so the description goes further: it enumerates the verdict outcomes, states that a missing state degrades to needs_state, describes the quoteUrl next step, and disclaims that results are estimates rather than approvals. It also confines the tool to non-owner-occupied business-purpose loans, which is real eligibility context an agent would otherwise miss.

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?

Purpose and output shape are front-loaded, and each sentence conveys either a capability, a prerequisite, or a limitation. Some padding exists in the layered disclaimer sentences, but nothing is genuinely wasted.

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?

With no output schema, the description carries the burden of describing returns and does so thoroughly: verdict set, largest allowable loan, follow-up questions, and the quoteUrl next step. Combined with the state prerequisite and eligibility scope, an agent has enough to call this correctly.

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 88%, so the schema already documents nearly all 17 parameters including enum values and the state requirement. The description adds only emphasis on propertyState's criticality, which the schema field description also states, so it does little beyond the structured data.

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?

A specific verb and resource ('check a real estate investment deal against published loan terms') plus the exact verdict vocabulary it produces. An agent can tell this apart from a program-listing sibling without reading a schema, since this evaluates a deal rather than enumerating products.

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 preconditions ('a verdict needs the property's state; without one the result is needs_state') and eligibility boundaries (business purpose, non-owner-occupied only). It stops short of explicitly naming when to use list_loan_programs instead, though the distinction is inferable.

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