Skip to main content
Glama

Search real estate fund managers

search_re_fund_managers
Read-onlyIdempotent

Advisers that swear a Real Estate Fund vehicle on Form ADV Schedule D 7.B.(1): one manager is one CRD, with its registration and latest filing, regulatory assets under management, the summed gross asset value of its non-feeder, non-quarantined real estate vehicles with its size band, vehicles current and ever, strategy class with its state and basis, operator model, property types and markets with their bases, validated property bindings and their loans, and the public plans that disclose commitments. Filter by state (the manager's headquarters), strategy class, size band, operator model, gross asset value, vehicles, property type, holdings or public LPs, and by ACTIVITY on its validated holdings: acquisitions or financings in the last 12 months, a loan maturing before a date, the latest vintage, the year of its first real estate vehicle (emerging managers). similar_to gives the managers with the same strategy class and a shared property type, the subject excluded. Sort by gav, acquisitions, financings, maturity, vintage, newest, loans, lps, recent. Every row carries its activity numbers. 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.

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": "search_re_fund_managers"
  }
}

Input Schema

NameRequiredDescriptionDefault
crdNo
sortNo
limitNo
queryNoManager name contains, or a CRD.
stateNoTwo-letter US state code.
cursorNonext_cursor from a previous page of this tool, unchanged.
raisingNoOnly managers with a vehicle whose published lifecycle is RAISING or FORMING, read over every such vehicle; each row's matched_on.raising names them. Combine with invested_state in ONE call for 'raising and has invested in X': two separate reads are a union, not both conditions.
size_bandNo
similar_toNoA real estate fund manager: a dfx:ref:<uuid> id or the manager's CRD.
with_loansNoOnly managers with at least one loan on a validated holding.
max_gav_usdNo
min_gav_usdNo
min_vehiclesNo
property_typeNoA property type on the manager's own list: MULTIFAMILY, INDUSTRIAL, OFFICE, RETAIL, HOTEL, MIXED_USE, LAND, STUDENT_HOUSING, SENIOR_HOUSING, SELF_STORAGE, SINGLE_FAMILY_RENTAL, DATA_CENTER, HEALTHCARE, LIFE_SCIENCE, MANUFACTURED_HOUSING, NET_LEASE, OTHER (words such as 'apartments' or 'data centers' are folded).
with_holdingsNoOnly managers with at least one validated property binding.
include_formerNoAlso managers whose latest filing no longer swears a real estate fund.
invested_stateNoTwo-letter state: only managers with validated property holdings there or loans on validated holdings there (their history in the state, not their headquarters, which is `state`). Each row's matched_on.invested_state says which, with loan principal labelled as debt.
operator_modelNo
strategy_classNoVALUE_ADD, CORE, OPPORTUNISTIC, DEBT... (a word such as 'value add' is folded to the vocabulary).
maturing_beforeNoISO date: the manager's next loan maturity falls between today and this date.
with_public_lpsNo
min_financings_12mNo
latest_vintage_fromNoIts newest vehicle's vintage is this year or later.
min_acquisitions_12mNoAcquisitions recorded at its validated holdings in the last 12 months, at least this many (1 = actively acquiring).
first_vehicle_year_fromNoIts first real estate vehicle on the tape is this year or later (emerging managers; the tape starts 2011).

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed2 schema fields changed
    • addedInput schema / properties / invested_state
      Added value: +{
      +  "description": "Two-letter state: only managers with validated property holdings there or loans on validated holdings there (their history in the state, not their headquarters, which is `state`). Each row's matched_on.invested_state says which, with loan principal labelled as debt.",
      +  "type": "string"
      +}
    • addedInput schema / properties / raising
      Added value: +{
      +  "description": "Only managers with a vehicle whose published lifecycle is RAISING or FORMING, read over every such vehicle; each row's matched_on.raising names them. Combine with invested_state in ONE call for 'raising and has invested in X': two separate reads are a union, not both conditions.",
      +  "type": "boolean"
      +}
  2. Changed10 schema fields changed
    • addedInput schema / properties / first_vehicle_year_from
      Added value: +{
      +  "description": "Its first real estate vehicle on the tape is this year or later (emerging managers; the tape starts 2011).",
      +  "type": "integer"
      +}
    • addedInput schema / properties / latest_vintage_from
      Added value: +{
      +  "description": "Its newest vehicle's vintage is this year or later.",
      +  "type": "integer"
      +}
    • addedInput schema / properties / maturing_before
      Added value: +{
      +  "description": "ISO date: the manager's next loan maturity falls between today and this date.",
      +  "type": "string"
      +}
    • addedInput schema / properties / min_acquisitions_12m
      Added value: +{
      +  "description": "Acquisitions recorded at its validated holdings in the last 12 months, at least this many (1 = actively acquiring).",
      +  "type": "integer"
      +}
    • addedInput schema / properties / min_financings_12m
      Added value: +{
      +  "type": "integer"
      +}
    • changedInput schema / properties / property_type / description
      Previous value: -"A property type on the manager's own list (MULTIFAMILY, INDUSTRIAL, OFFICE, RETAIL, ...)."New value: +"A property type on the manager's own list: MULTIFAMILY, INDUSTRIAL, OFFICE, RETAIL, HOTEL, MIXED_USE, LAND, STUDENT_HOUSING, SENIOR_HOUSING, SELF_STORAGE, SINGLE_FAMILY_RENTAL, DATA_CENTER, HEALTHCARE, LIFE_SCIENCE, MANUFACTURED_HOUSING, NET_LEASE, OTHER (words such as 'apartments' or 'data centers' are folded)."
    • addedInput schema / properties / similar_to
      Added value: +{
      +  "description": "A real estate fund manager: a dfx:ref:<uuid> id or the manager's CRD.",
      +  "type": "string"
      +}
    • changedInput schema / properties / sort / enum
      Previous value: -[
      -  "gav",
      -  "vehicles",
      -  "raum",
      -  "lps",
      -  "recent",
      -  "name"
      -]New value: +[
      +  "acquisitions",
      +  "financings",
      +  "gav",
      +  "loans",
      +  "lps",
      +  "maturity",
      +  "name",
      +  "newest",
      +  "raum",
      +  "recent",
      +  "vehicles",
      +  "vintage"
      +]
    • addedInput schema / properties / strategy_class / description
      Added value: +"VALUE_ADD, CORE, OPPORTUNISTIC, DEBT... (a word such as 'value add' is folded to the vocabulary)."
    • addedInput schema / properties / with_loans
      Added value: +{
      +  "description": "Only managers with at least one loan on a validated holding.",
      +  "type": "boolean"
      +}
  3. Added

TDQS

A3.9/5.0
Behavior5/5

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

Annotations already establish a safe read (readOnly, idempotent, non-open-world), and the description layers substantial extra context on top: entitlement truncation (first 5 rows in full, locked.count, locked.by_type), permanent withholding of contact values and decision-maker names, GAV semantics (never fund size/commitments/dry powder, quarantined readings excluded), and tape coverage starting 2011. This is unusually rich disclosure beyond the structured fields.

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 content is largely substantive (entitlement, GAV caveats, coverage window), but it is delivered as two enormous run-on sentences with no segmentation, making it hard to scan. Front-loading the purpose is good, yet a 25-parameter tool warrants clearer structure than a dense block.

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 25-param, no-output-schema tool, this covers the essentials an agent needs: filter vocabulary, sort keys, the state/invested_state distinction, activity semantics, coverage window, and access limits. Remaining gaps (return-shape of a row beyond field enumeration, pagination behavior with cursor) are modest given the enumeration of returned sections.

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?

With 25 parameters and only 60% schema description coverage, the description compensates well: it clarifies state as headquarters versus invested_state as holdings history, explains similar_to (same strategy class, shared property type, subject excluded), and unpacks similar_to's exclusion behavior. It doesn't walk every filter, but it resolves the parameters most prone to misreading.

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 opening clause pins the resource precisely: advisers swearing a Real Estate Fund vehicle on Form ADV Schedule D 7.B.(1), one row per CRD. That verb+resource and the 'one manager is one CRD' framing distinguish it from sibling tools like search_re_fund_vehicles or get_re_fund_manager, though no sibling is named explicitly.

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?

The description enumerates filters and sort keys in detail, which implies how to use the tool, but never states when to prefer it over search_re_fund_vehicles, search_re_fund_lenders or get_re_fund_manager, and offers no explicit exclusions or prerequisites for choosing between them.

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.