Skip to main content
Glama

Mortgage lending in a county (HMDA)

county_lending_market
Read-onlyIdempotent

What lenders reported for a U.S. county in the latest HMDA filing year: purchase, refinance and cash-out loans and applications by loan type (conventional, FHA, VA, USDA) against the national mix, and the denial rate with its base named. Describes a market, never a person; small counts are withheld. Give a county FIPS code, or a county name with its state.

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": "county_lending_market"
  }
}

Input Schema

NameRequiredDescriptionDefault
yearNooptional HMDA filing year; defaults to the latest published
stateNotwo-letter state code, needed with county
countyNocounty name, e.g. "Bexar" or "Los Angeles County"; give state too
county_fipsNo5-digit county FIPS code, e.g. "48029" for Bexar County, TX

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.1/5.0
Behavior4/5

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

Annotations already declare readOnly, idempotent, openWorld and non-destructive, so the safety profile is covered. The description adds genuinely non-obvious behavior: small counts are withheld (privacy suppression), defaults to the latest published filing year, and the denial rate's base is named — real constraints an agent must anticipate in results.

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 content is front-loaded and every sentence carries information, including the scope, the measure list, and the suppression caveat. The first sentence is long and clause-heavy, which slightly taxes scanning, but nothing is redundant.

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?

With no output schema, the description does the work of explaining what comes back — measures, loan-type breakdown, national comparison, denial rate — which is adequate for a read-only lookup. Ambiguity handling for county names and result granularity are left unstated, but nothing essential is missing.

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 the schema does not: county_fips and county+state are alternate identification paths, and state is specifically required when using county. That either/or relationship is absent from the schema, where no parameter is required.

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 names a specific resource and scope (HMDA-reported lending for a U.S. county in the latest filing year) and enumerates the measures returned: purchase/refinance/cash-out originations and applications by loan type, comparison against the national mix, and the denial rate. The clause 'Describes a market, never a person' cleanly separates it from person- or lender-level siblings.

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?

It gives invocation guidance ('Give a county FIPS code, or a county name with its state') and implies usage as a market-context lookup, but never states when to prefer this over loan_limit, llpa_cost, or government_loan_fees, nor any exclusion such as non-HMDA-covered lenders. Usage is implied rather than directed.

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