Skip to main content
Glama

Loans on real estate fund managers' holdings, with maturities and lenders

search_re_fund_loans
Read-onlyIdempotent

Loans bound to a real estate fund manager through a validated property binding: lender of record (labelled when it is the CMBS trust holding the note rather than the originator), instrument, amount with its basis, origination, recorded and maturity dates, whether still open, address, state and property type where recorded, and the source. Filter by manager (dfx id or CRD), a name in the manager, holding or address, lender, state, property type, instrument (cmbs, mortgage...), maturing within N days or a maturity range; open loans only by default. group_by=manager rolls the matched loans up per manager (loans, amount, next maturity, lenders): the answer to 'which managers have loans maturing in the next 24 months'. A manager without a validated holding has no loans here, which is coverage, not an absence of debt. Property type is recorded on a minority of CMBS rows. Gross asset value is a fund's assets on a filing date: never fund size, never commitments, never dry powder, and a quarantined reading enters no sum. The sworn ADV tape starts in 2011 and runs through the latest monthly filings DFX has read (coverage_live on the answer gives the years and counts), so a first report in 2011 or 2012 is a first sighting, not a formation. Holdings, properties, loans and lenders appear only where a property binding passed its blind labels, which is a few hundred managers. ACCESS: without a paid DFX plan on the vertical, a list returns its first 5 rows in full and a count of the rest by type (locked.count, locked.by_type), never the rows; a record names its subject and the first 3 related names per section; contact values (email, phone, profile URLs) and decision-maker names are never returned, only their types and counts. Every answer says what it withheld in entitlement and locked. Full access: DFX Intelligence, 7 days free at https://dfxintel.com/data-factory/plans.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
sortNomaturity
limitNo
queryNoManager, holding entity or address contains.
stateNoTwo-letter US state code.
cursorNonext_cursor from a previous page of this tool, unchanged.
lenderNoLender name contains.
group_byNo
open_onlyNo
maturity_toNo
maturity_fromNo
property_typeNooffice, multifamily, industrial, retail, hotel (where recorded).
manager_dfx_idNoA real estate fund manager: a dfx:ref:<uuid> id or the manager's CRD.
instrument_kindNo
maturing_within_daysNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. Added

TDQS

A4.5/5.0
Behavior5/5

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

With annotations covering the safety profile (readOnly, idempotent, non-destructive), the description adds rich behavioral context: coverage caveats (validated bindings, few hundred managers), data provenance (ADV tape from 2011, quarantined readings excluded from sums), and detailed access limits (first 5 rows without paid plan, withheld contact values). This goes far beyond annotations.

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?

The description is a dense wall of text with a long run-on first sentence listing returned fields, followed by filter guidance, data caveats, and access rules. While much of the information is valuable, some tangential details (e.g., gross asset value definitions) could be trimmed, and the structure is not optimally front-loaded.

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?

For a 14-parameter tool with no output schema and modest schema description coverage, the description is remarkably complete: it covers coverage, data quirks, access restrictions, and the shape of returned fields. It leaves little ambiguity about what the tool does or how its results should be interpreted.

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 43%, so the description must compensate; it explains the semantics of many filters (manager accepts dfx id or CRD, name search across manager/holding/address, instrument kinds, maturity windows) and the group_by rollup. It omits meaning for sort, limit, and cursor, but these are generic and partially covered by schema descriptions.

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 the specific resource (loans bound to a real estate fund manager via a validated property binding) and lists the exact fields returned, including the lender-of-record distinction between CMBS trust and originator. This scope differentiates it from sibling loan searches like search_cmbs_loans or search_re_fund_lenders, which lack the manager-holding binding requirement.

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?

It provides clear context through filter descriptions and a concrete example ('which managers have loans maturing in the next 24 months'), and states the default of open loans only. However, it does not explicitly name alternative tools or state when not to use this one, leaving the agent to infer exclusions.

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.