Skip to main content
Glama

Private funds an adviser reports on Form ADV

search_ria_funds
Read-onlyIdempotent

Private funds from Form ADV Schedule D 7.B.(1): fund name, SEC fund id (805-...), type, gross asset value with its as-of date (reported gross assets, NOT fund size or commitments), owners, minimum investment, ownership percentages, 3(c)(1) or 3(c)(7), master or feeder, first and last reported, status (reported or dropped) and the Form D file number where the adviser gave one. With include_custodians, each fund's custodians (question 25) with city, state, SEC number and LEI. Filter by adviser (dfx:ria: id or CRD), name, type, status, state, Form D number or minimum gross assets. Fund reporting after 2024-12-31 is roster counts only. With group_by=adviser and a fund_type, ranks advisers instead (which advisers manage the most real estate private fund gross assets): each adviser's CRD, Form ADV link, fund count, summed gross asset value and five largest funds by 805- id, over reported funds with gav_as_of in the last recency_months (default 24, stated in basis). A fund reporting more gross assets than its adviser's total RAUM is left out of the sums and listed in excluded_as_likely_misreported. 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_ria_funds"
  }
}

Input Schema

NameRequiredDescriptionDefault
sortNo
limitNo
queryNoFund name contains, an 805- fund id, or a 021- Form D file number.
stateNoTwo-letter US state code.
cursorNonext_cursor from a previous page of this tool, unchanged.
statusNoreported: on the adviser's latest filing; dropped: no longer reported.
group_byNoadviser: rank advisers by the summed gross asset value of their funds of fund_type (every type when none is given; basis says whether every fund was read).
fund_typeNo
firm_dfx_idNoAn RIA graph id of the form dfx:ria:<uuid> (from search_ria, resolve_name or search_entities), or the firm's CRD number as a string.
min_gav_usdNo
recency_monthsNoOnly funds whose gross asset value is dated within this many months. Default 24 with group_by; no window otherwise.
form_d_file_numberNo
include_custodiansNoAttach custodian rows to each fund on the page.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed2 schema fields changed
    • addedInput schema / properties / group_by
      Added value: +{
      +  "description": "adviser: rank advisers by the summed gross asset value of their funds of fund_type (every type when none is given; basis says whether every fund was read).",
      +  "enum": [
      +    "adviser"
      +  ],
      +  "type": "string"
      +}
    • addedInput schema / properties / recency_months
      Added value: +{
      +  "description": "Only funds whose gross asset value is dated within this many months. Default 24 with group_by; no window otherwise.",
      +  "maximum": 240,
      +  "minimum": 1,
      +  "type": "integer"
      +}
  2. Added

TDQS

A3.9/5.0
Behavior5/5

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

Goes well past the readOnly/idempotent annotations: it discloses that GAV is reported gross assets and not fund size or commitments, that post-2024-12-31 reporting is roster counts only, that funds exceeding adviser RAUM are excluded into excluded_as_likely_misreported, and the exact partial-access behavior (first 5 rows, locked counts, contact values never returned, entitlement/locked keys in every answer). This is the kind of context an agent cannot get from the 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?

The content is front-loaded correctly (resource and fields first, ranking mode, then access limits), and most sentences carry real information. But the field enumeration is a dense comma-run and the closing 'Full access: DFX Intelligence, 7 days free at https://…' is promotional text that does not help an agent select or invoke the tool.

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 13-parameter tool with no output schema and two distinct response modes, the description covers the important unknowns: mode switching, recency basis, exclusion logic, and degraded-access output shape. The remaining hole is sorting/pagination semantics, which the description and schema both leave silent.

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?

At 62% schema coverage the description compensates well: it explains what include_custodians attaches (question 25 with city, state, SEC number, LEI), what recency_months means in the ranking basis, that group_by=adviser changes the entire response shape, and that min_gav_usd filters on gross assets. Gaps remain — `sort` (gav/recent/name) and `cursor` are unexplained in both description and schema, and the 25-row cap is only implied by the entitlement text.

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?

Opens with a precise resource statement — 'Private funds from Form ADV Schedule D 7.B.(1)' — and enumerates exactly what each row carries (fund name, 805- id, type, GAV with as-of date, 3(c)(1)/3(c)(7), master/feeder, status). That is enough for an agent to tell it apart from search_pe_funds / search_vc_funds / search_re_fund_vehicles, though it never names a sibling explicitly to confirm the boundary.

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 through the filter list and the alternate ranking mode ('With group_by=adviser and a fund_type, ranks advisers instead'), which does tell an agent one important non-obvious branch. But there is no explicit 'use this instead of X when Y' guidance and no stated prerequisites or exclusions relative to the many neighboring fund-search tools.

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.