Skip to main content
Glama

DFX Real Estate Intelligence

by io.github.Capital-W-Holdings
OverviewDiscussionsAdmin

The one person most likely to own the decision, with distinct backups, why, route type and confidence

who_to_contact
Read-onlyIdempotent

For one organization (dfx_id, or its name in organization, resolved through the identity layer so every graph the institution is on is read) or one opportunity (opportunity_id from search_opportunities): ONE recommended person and up to two DISTINCT backups, ranked for a purpose (private_credit, advisor_recruiting, acquisitions, capital_raising, lending_desk, lp_fundraising ...). People come from every contact source DFX holds: the organization's own team pages, Form ADV Schedule A officers, sponsor and provider principals, private equity, venture, family office and allocator staff, and named contact routes. Each person carries title, role family, why they fit the purpose, decision authority (inferred from the title, or observed, labelled which), the contact route TYPES on record with their rights class (RESALEABLE, REVEALABLE, INTERNAL_USE) and verification, the kind and host of the evidence, and confidence by dimension. Never an email address, phone number or a person's page: routes are types only, and a person known only from a data provider is returned as a role with name null. If nobody on record holds a role that owns the purpose it says so and lists the roles that would; a generic inbox is never offered as a substitute. 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
limitNo
dfx_idNoA DFX id (dfx:<graph>:<uuid>) or a bare real estate UUID.
purposeNoWhat the caller wants to talk about; people are ranked for it.
organizationNoThe organization's name, when no dfx_id is at hand (e.g. 'Akoya Capital Partners').
opportunity_idNoAn opportunity id (opp_...) from search_opportunities.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed3 schema fields changed
    • addedInput schema / properties / organization
      Added value: +{
+  "description": "The organization's name, when no dfx_id is at hand (e.g. 'Akoya Capital Partners').",
+  "type": "string"
+}
    • changedInput schema / properties / purpose / description
      Previous value: -"What the caller wants to talk about; re-ranks people at an organization."New value: +"What the caller wants to talk about; people are ranked for it."
    • changedInput schema / properties / purpose / enum
      Previous value: -[
-  "acquisition",
-  "co_investment",
-  "consultant_search",
-  "credit_origination",
-  "distressed_credit",
-  "lp_fundraising",
-  "placement",
-  "property_capital",
-  "re_lending",
-  "recruiting",
-  "refinancing",
-  "ria_acquisition",
-  "sponsor_lender_relationship"
-]New value: +[
+  "acquisition",
+  "acquisitions",
+  "advisor_recruiting",
+  "capital_raising",
+  "co_investment",
+  "consultant_search",
+  "credit_origination",
+  "distressed_credit",
+  "lending_desk",
+  "lp_fundraising",
+  "placement",
+  "private_credit",
+  "property_capital",
+  "re_lending",
+  "recruiting",
+  "refinancing",
+  "ria_acquisition",
+  "sponsor_lender_relationship"
+]
  2. Added

TDQS

A4.6/5.0
Behavior5/5

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

With annotations already covering the safety profile (readOnly, idempotent, non-destructive, closed-world), the description still adds substantial context: entitlement gating (first 5 rows plus locked counts without a paid plan), what is never returned (emails, phones, URLs, decision-maker names), role-with-null-name fallback for data-provider-only people, and the refusal to substitute a generic inbox. That is well beyond what structured fields convey.

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?

Front-loaded with the core behavior and scope before the access details, which is the right ordering. It is a dense single block with some promotional filler (the free-trial URL) that could be trimmed, but essentially every other sentence carries functional information.

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?

There is no output schema, so the description must carry the return contract, and it does: per-person fields (title, role family, why, decision authority with inferred/observed labelling), route types with rights class and verification, evidence kind/host, confidence dimensions, plus the entitlement/locked envelope. For a no-output-schema tool this is complete.

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 80%, so most parameters are self-documented, but the description adds real meaning: dfx_id is resolved through the identity layer so every graph the institution is on is read, organization is a name fallback, and opportunity_id is sourced from search_opportunities. It only omits guidance on limit, which is 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+resource: returns ONE recommended person plus up to two DISTINCT backups for a named purpose, scoped to one organization or one opportunity. It clearly distinguishes itself from generic lookups like search_people by emphasizing a single ranked decision-owner rather than a list, and from who_should_care/who_should_provider_call by naming the exact subject type and output shape.

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 conditions for use: one org (dfx_id or organization name) or one opportunity (opportunity_id), with an enumerated purpose vocabulary. However it never states when NOT to use it or names the obvious alternatives (search_people, who_should_care, who_should_provider_call), so routing between siblings 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