Skip to main content
Glama

Fannie Mae price adjustment (LLPA) for a scenario

llpa_cost
Read-onlyIdempotent

Fannie Mae's published loan-level price adjustment (LLPA) for an anonymized conventional scenario (Classic FICO, LTV, loan amount, purpose, occupancy, property type), the dollar price it adds, and the structuring moves that lower it, with the matrix edition. An LLPA is a one-time price adjustment, never an interest rate and never a credit decision; the lender decides. Takes numbers only, never a borrower's name or details.

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": {
      "fico": "<fico>",
      "ltv": "<ltv>",
      "loan_amount": "<loan_amount>"
    },
    "name": "llpa_cost"
  }
}

Input Schema

NameRequiredDescriptionDefault
ltvYesloan-to-value, e.g. "90" or "80.5%". Read as Fannie Mae does (Selling Guide B2-1.2-01): truncated to two decimals, then rounded up to the whole percent.
ficoYesrepresentative Classic FICO score, e.g. 740. VantageScore 4.0 pricing is not loaded, so a VantageScore must not be given here: Fannie Mae's 09/30/2026 reissue of LL-2026-06 removed the separate VantageScore 4.0 grids, and DealMatcher has not encoded how a VantageScore is priced now.
purposeNo
homereadyNo
occupancyNo
minimum_miNotrue if the loan uses Fannie Mae's minimum mortgage insurance coverage option (adds the Minimum-MI charge)
term_yearsNoloan term in years; defaults to 30 and the answer says so. Fannie Mae's purchase and limited cash-out score grids apply only to terms over 15 years.
loan_amountYesdollar amount, e.g. "$360,000"
amortizationNo
high_balanceNotrue if the loan is above the county baseline (high-balance)
mh_advantageNomanufactured home only: true if it meets MH Advantage (no manufactured-home charge)
duty_to_serveNotrue if the loan may meet a Duty to Serve category (flagged as a possible waiver, never applied)
property_typeNoDETACHED_CONDO and COOP do not pay the condo charge (matrix footnote 1)
first_time_homebuyerNo
subordinate_financingNotrue if there is a second lien (CLTV above LTV)

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A3.9/5.0
Behavior4/5

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

Annotations already declare read-only, idempotent, non-destructive, closed-world behavior, so the bar is lower. The description still adds real substance: an LLPA is a one-time price adjustment, not a rate or credit decision, and the lender decides. It does not cover failure modes (e.g., what happens with unsupported inputs) but goes meaningfully beyond the annotations.

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?

Two dense sentences with no filler; the output content is front-loaded, followed by the semantic guardrail and the privacy constraint. Slightly overpacked with parenthetical enumerations that restate schema fields, but nothing is wasted.

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 15-parameter pricing calculator with no output schema, the description conveys what comes back (dollar adjustment, structuring moves, matrix edition) and the critical framing that this is informational, not a credit decision. Missing only scope boundaries relative to sibling fee tools, which keeps it from a 5.

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 67% and the schema itself carries strong enum and pattern semantics, including detailed notes on FICO rounding, VantageScore exclusion, and footnote-driven property types. The description adds only the scenario framing (Classic FICO, LTV, loan amount, purpose, occupancy, property type) and the numbers-only constraint, which is useful but not compensating for the undocumented parameters.

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 resource (Fannie Mae's published LLPA matrix) and enumerates the scenario inputs and outputs (dollar price, structuring moves, matrix edition). Clear enough to distinguish it from siblings like government_loan_fees or loan_limit, which cover different fee/limit domains.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines3/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Usage is implied rather than stated: the description makes clear this is a pricing lookup for a conventional scenario, and the 'never a credit decision' clause hints at its advisory role. But it never explicitly says when to prefer this over government_loan_fees or loan_limit, nor what to do when the scenario is non-conventional or out of scope.

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