Skip to main content
Glama

Origen Capital

Look up community lenders for a US county

origen_financing_lookup

The CDFIs, low-income credit unions, SBA microloan intermediaries, and ITIN-friendly national nonprofits serving a US county — the lenders that say yes when a bank says no. By lane (business, home, personal), in English or Spanish. Splits institutions headquartered in the county from those with only a walk-in branch there; a county with no door at all is answered honestly with the state tier. Every record names its federal source and vintage. Public federal data; nobody pays to be listed; no borrower information is asked or taken.

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": {
      "lane": "<lane>",
      "county": "<county>",
      "state": "<state>"
    },
    "name": "origen_financing_lookup"
  }
}

Input Schema

NameRequiredDescriptionDefault
itinNotrue when the borrower has an ITIN and no SSN — the answer leads with verified ITIN-friendly options
laneYes'business', 'home', or 'personal' — plain words and Spanish work too ('negocio', 'vivienda', 'préstamo personal')
stateYesUS state name or two-letter code, e.g. 'Texas' or 'TX'
typesNoOptional: keep only these kinds of institution (any match). Omit for all.
countyYesUS county name, e.g. 'Harris County'. A city name also works and resolves to its county ('Houston' → Harris County).
languageNoAnswer language, default 'en'

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?

With no annotations at all, the description carries the full disclosure burden and does a solid job: it states the geographic tiering logic (headquartered vs. walk-in branch, state-tier fallback), that every record carries its federal source and vintage, and that the data is public with no pay-for-listing and no borrower data collected. It stops short of describing the response shape or ordering beyond the ITIN-leading hint, so result volume and sorting remain unknown.

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?

Information is front-loaded: what the tool returns, then the geographic split, then sourcing and data-policy claims. A few phrases are promotional rather than load-bearing ('the lenders that say yes when a bank says no,' 'nobody pays to be listed'), and the provenance/pay-to-play sentence is more marketing than agent-relevant behavior.

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 six-parameter, three-required read tool with no annotations and no output schema, the description supplies the behavior an agent actually needs: lane and language coverage, ITIN handling, the headquarters/branch/state-tier fallback, and source attribution. It never touches error handling for an unresolvable county or the shape of returned records, which is the remaining gap.

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 description coverage is 100%, so the schema already explains lane, county/city resolution, state, types, language, and ITIN — the description adds only one genuinely new semantic: that an ITIN request 'leads with verified ITIN-friendly options,' which affects result ordering. It says nothing about the types filter or the city-to-county resolution beyond what the schema states, so the baseline of 3 is appropriate.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description names the exact resource returned — CDFIs, low-income credit unions, SBA microloan intermediaries, and ITIN-friendly national nonprofits serving a US county, split by lane and by headquarters vs. branch presence. That is far more specific than a restatement of the name. It does not explicitly name or contrast against the sibling tools (origen_financing_coverage, origen_home_loan_approvals, origen_institution), so the reader must infer the boundary from the word 'lenders.'

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?

Usage context is clear and concrete: 'the lenders that say yes when a bank says no,' by lane, for English or Spanish speakers, with ITIN borrowers called out. It also sets expectations for the empty-result case ('a county with no door at all is answered honestly with the state tier'). What is missing is any explicit when-not or alternative — nothing tells an agent when to reach for origen_financing_coverage or origen_institution instead.

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