DFX Intelligence

Private equity transactions

search_pe_transactions

Read-onlyIdempotent

Acquisitions, add-ons, recapitalisations, carve-outs, secondary sales and exits on the private equity graph: type, status, announced and closed dates, target with industry and state, platform for an add-on (with the basis for calling it one), control, every party with role, side and attribution, and money (enterprise value, purchase price, equity value, target revenue and EBITDA) ONLY where disclosed, each beside its basis. An undisclosed amount is absent, never estimated. Filter by firm (any party), target, platform, type, target state, since and until dates (the announced date), add-ons only, control or target name. Newest first. partial=true means more rows exist: pass pagination.next_cursor to walk back to the firm's first deal. A firm search carries total (distinct deals) when counted. 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

Name	Required	Description
`limit`	No
`query`	No	NAME FILTER ONLY: the target's or any party's name contains. Never a sector or place; use sector and state.
`since`	No	ISO date; transactions announced on or after.
`state`	No	Two-letter US state code of the target.
`until`	No	ISO date; transactions announced on or before. Walk back through a firm's history with it.
`cursor`	No	pagination.next_cursor from the previous page, sent with the same filters: the next, older page.
`sector`	No	The target's industry as the graph classified it (technology, industrials, healthcare, consumer, construction_engineering, business_services, energy, environmental, financial_services, education, transportation_logistics, home_services, aerospace_defense, automotive). Plain words are mapped (software to technology). About half of transactions carry an industry; one without is not returned by this filter.
`add_on_only`	No
`firm_dfx_id`	No	A dfx:pe: firm or person id; returns transactions where it is any party (sponsor, buyer, seller, co-investor, lender, adviser, deal partner).
`target_dfx_id`	No	A private equity graph id of the form dfx:pe:<uuid>, as returned by search_pe_firms, search_pe_funds, search_pe_platforms or search_entities.
`control_status`	No
`platform_dfx_id`	No	A private equity graph id of the form dfx:pe:<uuid>, as returned by search_pe_firms, search_pe_funds, search_pe_platforms or search_entities.
`transaction_type`	No

Schema Changelog

Changes observed during successful MCP inspections.

Changed2 schema fields changedOct 30, 2026

addedInput schema / properties / cursor

Added value: +{
+  "description": "pagination.next_cursor from the previous page, sent with the same filters: the next, older page.",
+  "type": "string"
+}

addedInput schema / properties / until

Added value: +{
+  "description": "ISO date; transactions announced on or before. Walk back through a firm's history with it.",
+  "type": "string"
+}

Changed2 schema fields changedOct 1, 2026

changedInput schema / properties / query / description

Previous value: -"Target company name contains."New value: +"NAME FILTER ONLY: the target's or any party's name contains. Never a sector or place; use sector and state."

addedInput schema / properties / sector

Added value: +{
+  "description": "The target's industry as the graph classified it (technology, industrials, healthcare, consumer, construction_engineering, business_services, energy, environmental, financial_services, education, transportation_logistics, home_services, aerospace_defense, automotive). Plain words are mapped (software to technology). About half of transactions carry an industry; one without is not returned by this filter.",
+  "type": "string"
+}

AddedSep 14, 2026

TDQS

A4.6/5.0

Behavior5/5

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

Goes well beyond the readOnly annotations: discloses that undisclosed amounts are absent rather than estimated, that partial=true means more rows exist and how to page back, what a firm search returns as a total, and precisely how entitlement gating truncates lists (5 rows + locked counts by type) and redacts contact values and decision-maker names. This is exactly the behavioral context annotations cannot carry.

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?

Returned fields are front-loaded and the key constraints (disclosed-only money, partial/cursor, entitlement) follow logically. It is dense and slightly repetitive ('each beside its basis', the plan CTA) but nearly every sentence carries information an agent needs.

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 13-parameter, no-output-schema search tool, the description covers return shape, ordering, pagination, financial-field caveats, and access/redaction behavior comprehensively. An agent has enough to call it correctly and interpret partial and entitlement results without guessing.

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 69%, and the description compensates by naming the filter set and clarifying that since/until apply to the announced date and that firm matching is 'any party'. It adds real meaning for money fields and the platform/add-on basis, though a few params (limit, add_on_only, control_status enums) are left entirely to the schema.

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 and resource (search PE transactions) and enumerates the deal types and the exact fields returned (parties with role/side, enterprise value, purchase price, etc.). It distinguishes itself from sibling search tools by emphasizing the transaction graph, money-with-basis semantics, and the add-on/platform relation, so an agent can tell it apart from search_sponsor_deals or search_pe_platforms.

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?

Gives clear usage context: it enumerates the usable filters (firm as any party, target, platform, type, state, date range, add-ons only, control) and states ordering (newest first) and pagination semantics. It does not explicitly name an alternative sibling or state when NOT to use it, so it falls short of a 5.

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

All DFX Intelligence tools Inspect

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.

Private equity transactions

Input Schema

Schema Changelog

TDQS

Glama MCP Gateway

Resources