Skip to main content
Glama

DFX Real Estate Intelligence

by io.github.Capital-W-Holdings
OverviewDiscussionsAdmin

Company financings, labelled round or Form D

search_vc_financings
Read-onlyIdempotent

Companies on the venture graph that raised since a date, each financing labelled an ANNOUNCED ROUND (press: round type, stage, amount where disclosed) or an SEC FORM D OFFERING (never called a round: no stage, lead or investors). sector is matched on the company's own words, every term required ('enterprise ai' needs both). debt_only keeps offerings that include debt securities. order_by=amount ranks by the financing's amount, largest first, one row per company: the read for 'largest venture rounds of 2026' (since=2026-01-01, order_by=amount) and 'biggest raises this quarter'. Use for 'which AI companies raised recently', 'companies that raised debt', 'Series A rounds in fintech this quarter'. 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
cityNo
kindNo
limitNo
sinceNoYYYY-MM-DD; default 180 days ago.
stateNoTwo-letter US state code.
untilNoYYYY-MM-DD; financings on or before this date (order_by=amount).
sectorNo
order_byNodate (default): most recent first. amount: largest first.
debt_onlyNo
within_daysNo
venture_backed_onlyNoKeep companies with a venture investor on record (use when the question says venture-backed).
include_out_of_scopeNoDefault false: a manager's own fund raise, a fund vehicle's Form D, a public or holding company, a non-venture issuer or a large raise with no venture investor is left out and counted.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed2 schema fields changed
    • changedInput schema / properties / include_out_of_scope / description
      Previous value: -"order_by=amount only. Default false: a manager's own fund raise, a fund vehicle's Form D or a large raise with no venture investor is left out of the ranking and counted."New value: +"Default false: a manager's own fund raise, a fund vehicle's Form D, a public or holding company, a non-venture issuer or a large raise with no venture investor is left out and counted."
    • addedInput schema / properties / venture_backed_only
      Added value: +{
+  "description": "Keep companies with a venture investor on record (use when the question says venture-backed).",
+  "type": "boolean"
+}
  2. Changed1 schema field changed
    • addedInput schema / properties / include_out_of_scope
      Added value: +{
+  "description": "order_by=amount only. Default false: a manager's own fund raise, a fund vehicle's Form D or a large raise with no venture investor is left out of the ranking and counted.",
+  "type": "boolean"
+}
  3. Added

TDQS

A4.5/5.0
Behavior5/5

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

Annotations only cover read-only/idempotent/openWorld=false, but the description discloses substantial behavior beyond them: entitlement gating (first 5 rows plus locked.count/locked.by_type without a paid plan), which fields are never returned (contact values, decision-maker names), and the semantics of round vs Form D labelling. This is exactly the extra behavioral context the annotations don't 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?

Dense but front-loaded: scope, labelling, filter semantics, then the headline use cases, all before the access caveats. It is somewhat overloaded, and the trailing sales pitch ('Full access: DFX Intelligence, 7 days free at...') is promotional rather than functional, but nearly every other sentence earns its place.

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 12-param, no-output-schema, read-only tool, the description supplies the gating behavior, the row/record limits, the labelling model, and ordering semantics an agent needs. It is slightly incomplete on a few undocumented parameters (within_days) and does not describe pagination/limit behavior, but the important call-shaping context is present.

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 50% schema coverage the description must compensate, and it does for the load-bearing params: sector ('matched on the company's own words, every term required'), debt_only ('keeps offerings that include debt securities'), and order_by/amount ('ranks by financing amount, largest first, one row per company'). Gaps remain for within_days and city/state/kind, which are unexplained in both schema and description.

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 precise verb+resource and scope: companies on the venture graph that raised since a date, with each financing explicitly typed as an ANNOUNCED ROUND or an SEC FORM D OFFERING. It goes further by defining what a Form D is not (never a round; no stage/lead/investors), letting an agent distinguish the two result classes without opening the schema.

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 concrete triggering queries ('largest venture rounds of 2026', 'biggest raises this quarter', 'which AI companies raised recently') and the parameter combos that serve them. However it never names a competing sibling (e.g. search_vc_investments, search_vc_raise_candidates) or states when NOT to use this tool, so routing against alternatives is left to inference.

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