Skip to main content
Glama

DFX Real Estate Intelligence

by io.github.Capital-W-Holdings
OverviewDiscussionsAdmin

Search private equity firms

search_pe_firms
Read-onlyIdempotent

Private equity firms (management companies and advisers) as compact cards: the classifier's class with its state, confidence and basis; size band with the evidence it was sized on; fund counts, latest vintage and Form ADV gross assets reported for private equity funds since 2024 (reported gross assets, NOT fund size or dry powder); portfolio and transaction counts (36 and 12 months); team counts; acquisition appetite and investment velocity values. Filter by name, sector, class, class_state, size_band, state or minimum transactions in 36 months. A sector word (software, healthcare, industrials) goes in sector, never in query, which matches firm names only. Returns dfx:pe: ids. Funds, people, transactions, scores with their components and counterparties are on get_pe_firm, not on these cards. Not for family offices, independent sponsors or venture firms (search_family_offices, search_independent_sponsors, search_vc_firms). 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
sortNotransactions (default): most deals in 36 months; gav: reported PE gross assets; recent: latest event; funds: private equity fund count.
classNoThe classifier's verdict. CANDIDATE_PE is a name on the universe that has not been ruled on; firms with no class yet are also candidates and are excluded by any class filter. NOT_PE rows are never published.
limitNo
queryNoNAME FILTER ONLY: firm name contains, e.g. 'Audax'. Punctuation is ignored. Never a sector, strategy or place: 'software' here returns firms whose NAME contains software.
stateNoTwo-letter US state code.
cursorNonext_cursor from a previous page of this tool, unchanged.
sectorNoA sector the firm states it invests in, from its own website criteria (about 2,100 firms state one): technology, software, financial_services, consumer, healthcare, infrastructure, energy, industrials, real_estate, business_services, manufacturing, media_telecom, environmental_services, transportation_logistics, distribution, life_sciences, food_beverage, education, building_products, agriculture, aerospace_defense, hospitality_leisure, franchising, safety_security, chemicals_materials, industrial_services, packaging, automotive, government_contracting, specialty_distribution. Plain words are mapped (saas to software, health to healthcare, fintech to financial_services). A firm that states no sectors is not returned by this filter.
size_bandNoLOWER_MIDDLE_MARKET, MIDDLE_MARKET, UPPER_MIDDLE_MARKET, LARGE_CAP, or UNSIZED (no size evidence yet, not 'small'). Each card names the basis the band was assigned on.
class_stateNoHow settled the class is. confirmed means evidence the classifier treats as decisive; probable is a strong inference.
min_transactions_36mNoAt least this many transactions as sponsor, buyer, co-investor or minority investor announced in the last 36 months.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed2 schema fields changed
    • changedInput schema / properties / query / description
      Previous value: -"Firm name contains, e.g. 'Audax'. Punctuation is ignored."New value: +"NAME FILTER ONLY: firm name contains, e.g. 'Audax'. Punctuation is ignored. Never a sector, strategy or place: 'software' here returns firms whose NAME contains software."
    • addedInput schema / properties / sector
      Added value: +{
+  "description": "A sector the firm states it invests in, from its own website criteria (about 2,100 firms state one): technology, software, financial_services, consumer, healthcare, infrastructure, energy, industrials, real_estate, business_services, manufacturing, media_telecom, environmental_services, transportation_logistics, distribution, life_sciences, food_beverage, education, building_products, agriculture, aerospace_defense, hospitality_leisure, franchising, safety_security, chemicals_materials, industrial_services, packaging, automotive, government_contracting, specialty_distribution. Plain words are mapped (saas to software, health to healthcare, fintech to financial_services). A firm that states no sectors is not returned by this filter.",
+  "type": "string"
+}
  2. Added

TDQS

A4.8/5.0
Behavior5/5

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

Annotations already cover read-only/idempotent safety, and the description adds substantial behavioral context beyond them: unentitled responses return first 5 rows plus locked.count/locked.by_type, records are truncated to 3 related names per section, contact values and decision-maker names are never returned, and every answer discloses withholding via `entitlement`/`locked`. This is unusually rich disclosure for a search tool.

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?

Very dense and mostly front-loaded: identity and card contents come first, then filters, then entitlement. Some material (e.g. the parenthetical reminder about reported gross assets vs dry powder, and the promotional 'Full access: DFX Intelligence, 7 days free at...') is not strictly needed for correct invocation and slightly pads the text.

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?

With no output schema and 10 parameters, the description carries the return-value burden and does so: it states the id format (dfx:pe: ids), which fields appear on cards, that funds/people/transactions/scores require get_pe_firm, and how entitlement degrades results. Nothing an agent needs to call or interpret the tool is missing.

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 already 90%, so the baseline is 3, but the description adds genuine cross-parameter guidance the schema does not: the sector-vs-query boundary is restated and reinforced, size_band is explained as evidence-based rather than a proxy for 'small' (UNSIZED ≠ small), and min_transactions_36m spells out the roles counted (sponsor, buyer, co-investor, minority).

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?

States a specific verb+resource (search private equity firms) and enumerates exactly what a card contains: classifier class/state/confidence/basis, size band with evidence, fund counts, Form ADV gross assets, portfolio/transaction counts, team counts, appetite and velocity. It explicitly distinguishes itself from get_pe_firm (detail records) and from the family-office/independent-sponsor/VC siblings.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines5/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Gives explicit when-not conditions ('Not for family offices, independent sponsors or venture firms') with named alternative tools, and steers input choice ('a sector word goes in `sector`, never in `query`'). It also clarifies that funds/people/transactions live on get_pe_firm rather than here.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

All DFX Real Estate Intelligence toolsInspect
Try in Browser
One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources