Skip to main content
Glama

FreeRateUpdate Mortgage & Home Equity Shopping

Lender directory with NMLS numbers

get_lender_universe
Read-onlyIdempotent

Search FreeRateUpdate's published lender pages: every company the public page resolver publishes on freerateupdate.com/reviews/, and nothing else. A row shows only what that page shows: the display name, the company NMLS, the states the page shows (currently none: fru-com's licensing projection is off), and the page URL. No internal ids, aliases, crosswalks or status labels. Eligibility is decided before the limit: the limit never draws a company whose page is hidden, redirected away or rejected by the identity check back in. A returned match is evidence FRU holds the identity; absence from the list is not proof it does not. FRU never publishes which lender has the best rate. One row per company; a DBA brand page is the same company's row. count is the full deduplicated match count (one row per company), while rows return at most limit of them (25 by default, up to 200): a count above the rows returned means the response is truncated, so absence from one response is not absence.

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": "get_lender_universe"
  }
}

Input Schema

NameRequiredDescriptionDefault
qNoName / DBA alias / bank-name substring (a matching key only; the row still shows only what the page shows)
limitNoDefault 25
stateNoOptional 2-letter state; matches the states the page shows (currently none, so this returns no rows until fru-com turns its licensing projection on)

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed3 schema fields changed
    • removedInput schema / properties / active
      Removed value: -{
      -  "description": "Optional filter on the active/not-active attribute only (never on verification): true = currently active in the network only; false = not currently active only. Omit to return both.",
      -  "type": "boolean"
      -}
    • changedInput schema / properties / q / description
      Previous value: -"Name / DBA alias / bank-name substring"New value: +"Name / DBA alias / bank-name substring (a matching key only; the row still shows only what the page shows)"
    • changedInput schema / properties / state / description
      Previous value: -"Optional 2-letter state"New value: +"Optional 2-letter state; matches the states the page shows (currently none, so this returns no rows until fru-com turns its licensing projection on)"
  2. First observed

TDQS

A4/5.0
Behavior5/5

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

With readOnly/openWorld/idempotent already declared, the description still adds substantial behavioral context: eligibility is resolved before the limit is applied so hidden, redirected, or identity-rejected pages never consume rows; one row per company with DBA pages collapsed; count is the full deduplicated match count versus a capped row list. These are non-obvious traits an agent could not recover from the annotations or schema.

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?

It is front-loaded with the row contract first, which is good, but it runs long and repeats the absence caveat twice ("absence from the list is not proof" and "absence from one response is not absence"). The aside "FRU never publishes which lender has the best rate" does not help an agent call the tool and is a non sequitur here.

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?

There is no output schema, and the description compensates by specifying the return shape (row fields), the count-versus-rows relationship, and deduplication rules. Combined with the eligibility and truncation caveats, an agent has everything needed to call this correctly and interpret the result, including the currently-degenerate state filter.

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 real meaning about how parameters interact: the limit is applied after eligibility filtering, and the gap between count and returned rows signals truncation. That interaction semantics is not expressible in the per-field schema and directly changes how an agent should set limit.

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 states a concrete verb and resource ("Search FreeRateUpdate's published lender pages") and enumerates exactly what a row contains: display name, company NMLS, states, page URL. It also draws a boundary with "No internal ids, aliases, crosswalks or status labels," which implicitly separates it from profile/score siblings, though it never names an alternative tool the way a 5 would.

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 prescribed: an agent can infer this is the discovery/directory lookup, but there is no explicit "use this when X, use get_lender_profile when Y." The description does supply valuable usage-adjacent rules — that absence from a response is not proof of non-existence, and that a count above rows returned means truncation — which raise it above bare minimum.

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