Skip to main content
Glama

What is likely to happen next, with how well each pattern was measured

search_forward_opportunities
Read-onlyIdempotent

Forward opportunities across DFX: an entity, the event a measured pattern points to (a borrower reaching non-accrual, a pension plan re-upping with a manager, an RIA entering succession, a nursing home closing), the horizon, the pattern's lift over its base rate with the lower bound of its interval and a band (BASELINE, ELEVATED, HIGHLY_ELEVATED, EXCEPTIONAL, cut on the lower bound), an economic range with its unit, dated why-now facts, the evidence labelled by kind, confidence by dimension, and whether a person is identified. Each row says whether it may be read as 'likely to' (a VALIDATED pattern) or only as an emerging indicator. The likelihood belongs to the pattern, never to the entity: do not restate a lift as the chance this entity acts. Filter by vertical, predicted event, persona, horizon, economic size, band, contact coverage or entity. Rows come ranked by the model's entity rank (rank.position, rank.family_percentile). Use FIRST for any question about what is likely, next, near-term, about to happen, or who shows indicators. Say which status each row has: VALIDATED may be described as a measured pattern; TESTING and PROSPECTIVE_ONLY are emerging indicators and must not be called predictions. An empty answer means no governed forward row matches, not that nothing is developing: then say plainly that DFX has no validated forward signal for it (get_forward_signal_ledger shows what was tested and failed), and never offer completed events (a move that happened, a completed succession) as a forecast. 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
cursorNonext_cursor from a previous page of this tool, unchanged.
contactNoactionable: a decision maker with a professional email, LinkedIn or direct line. any_person: a named decision maker at least. Flags only; no contact value is returned.
personaNoThe reader the row was framed for (e.g. lend, acquire, serve, distribute, raise); matches the row's persona or any of its applicable_personas.
evidenceNovalidated: only patterns that may be read as 'likely to'. any: also emerging indicators, labelled.any
min_bandNo
verticalNo
within_daysNoHorizon ends on or before today plus this many days.
max_economicNoeconomic_low at most this, in the row's unit.
min_economicNoeconomic_high (or economic_low where no high) at least this, in the row's unit.
entity_dfx_idNoA DFX id (dfx:<graph>:<uuid>): forward rows about this entity.
predicted_eventNoThe event, as the ledger names it (e.g. NON_ACCRUAL, ADVISOR_MOVE); contains match.
opportunity_typeNoContains match on the opportunity type.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed2 schema fields changed
    • addedInput schema / properties / contact
      Added value: +{
      +  "description": "actionable: a decision maker with a professional email, LinkedIn or direct line. any_person: a named decision maker at least. Flags only; no contact value is returned.",
      +  "enum": [
      +    "actionable",
      +    "any_person"
      +  ],
      +  "type": "string"
      +}
    • changedInput schema / properties / persona / description
      Previous value: -"The reader the row was framed for (e.g. lend, recruit, raise)."New value: +"The reader the row was framed for (e.g. lend, acquire, serve, distribute, raise); matches the row's persona or any of its applicable_personas."
  2. Added

TDQS

A4.3/5.0
Behavior5/5

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

Annotations cover only the read-only/idempotent safety profile, and the description adds substantial context beyond them: entitlement gating (first 5 rows plus locked.count/by_type, no contact values or decision-maker names), status semantics (VALIDATED vs TESTING/PROSPECTIVE_ONLY), the cardinal rule that likelihood belongs to the pattern not the entity, and default ranking by rank.position.

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 purpose is front-loaded, but the body is a dense run-on covering row anatomy, status rules, empty-result handling, entitlement behavior and a plan URL, with repetition around what is withheld. It is informative but over-packed rather than tight.

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, no-output-schema tool, the description covers the shape of returned rows, ranking, status labeling, empty-result meaning and entitlement withholding. It is nearly complete, though it leaves some filter parameters (limit, cursor, opportunity_type) to the schema.

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 77%, so the schema carries most parameters, but the description adds real meaning: min_band is 'cut on the lower bound', economic filters are in the row's unit, and the filter surface (vertical, predicted event, persona, horizon, economic size, band, contact coverage, entity) is summarized. It does not explain limit/cursor or the exact enum semantics of min_band.

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?

The opening ('Forward opportunities across DFX') states a clear resource, and the row-by-row enumeration makes the return semantics explicit. It distinguishes itself from siblings like search_opportunities and search_signals indirectly via the 'likely to happen next' framing, but never names them, so the sibling differentiation is incomplete.

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?

It gives an explicit routing rule ('Use FIRST for any question about what is likely, next, near-term, about to happen, or who shows indicators'), names the alternative for the negative case (get_forward_signal_ledger shows what was tested and failed), and states a hard exclusion (never offer completed events as a forecast).

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.