FactLot

LP/GP equity distribution waterfall

calc_equity_waterfall

Read-onlyIdempotent

Split periodic project equity cash flows between LP and GP: preferred return (compounding or simple) and return of capital pro rata to capital in either order, an optional GP catch-up, IRR-hurdle tiers with promote splits measured on the LP's IRR, and a residual split. Returns per-period LP and GP contributions and distributions (with the GP's promote) that foot to the cent, and LP, GP, and project IRRs and multiples, with the conventions to confirm against the operating agreement. Deterministic: use this instead of doing the math yourself; cite formula calc.equity_waterfall@1 and the returned steps, and surface any warnings.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "cash_flows": "<cash_flows>",
      "lp_share": "<lp_share>"
    },
    "name": "calc_equity_waterfall"
  }
}

Input Schema

Name	Required	Description	Default
`pref`	No	Preferred return on unreturned capital, paid to all investors pro rata to capital. Omit for none.
`tiers`	No	IRR-hurdle tiers after the catch-up, in increasing until_irr order: each distributes with its promote until the LP's IRR reaches until_irr.
`catch_up`	No	GP catch-up after the pref and return of capital. Omit for none.
`lp_share`	Yes	Share of every contribution funded by the LP, e.g. 0.9; the GP co-invests the rest (1 for no GP capital). Capital, pref, and the non-promote part of every split are shared in this ratio.
`cash_flows`	Yes	Project-level equity cash flows at t = 0, 1, 2, … periods: negative = capital contributed by the investors, positive = cash available to distribute. At most 600.
`periods_per_year`	No	Cash-flow periods per year: 1 annual, 4 quarterly, 12 monthly. Sets the pref accrual per period and annualizes the IRRs.
`residual_promote`	No	GP promote share of everything after the last tier, e.g. 0.3 for a 70/30 split.
`distribution_order`	No	Which comes first from each distribution: accrued pref, then return of capital (the usual order), or capital first.	pref_then_capital

Schema Changelog

Changes observed during successful MCP inspections.

AddedNov 4, 2026

TDQS

A4.4/5.0

Behavior4/5

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

Annotations already declare readOnly/idempotent/non-destructive, so the description's added value is elsewhere: it discloses that results are deterministic, that outputs 'foot to the cent', that per-period LP/GP contributions and distributions are returned with the GP's promote broken out, that IRRs and multiples are included, and that warnings may be raised. That goes well beyond the annotations. It does not describe failure behavior for invalid input (e.g. catch_up.target_promote ≥ gp_share) or how warnings are surfaced.

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 verb and scope, and every clause carries information; nothing is redundant with the title. The downside is that it is a single dense ~90-word sentence-chain rather than a structured list, which makes the operational directives (determinism, citation, warnings) easy to miss at the tail.

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, the description carries the return-value burden itself and does so: per-period LP/GP contributions and distributions including promote, LP/GP/project IRRs and multiples, and reconciliation to the cent. Combined with a fully documented eight-parameter nested schema, an agent has everything needed to call and interpret the result.

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 100%, so the baseline is 3, but the description adds relational meaning the per-parameter text does not: it establishes the sequencing (pref and return of capital, then catch-up, then IRR tiers, then residual) and clarifies that promote splits are 'measured on the LP's IRR'. That pipeline context is what makes the eight parameters interpretable as one coherent model rather than isolated fields.

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?

Opens with a specific verb and resource ('Split periodic project equity cash flows between LP and GP') and then enumerates the exact mechanics covered: preferred return compounding/simple, return of capital ordering, GP catch-up, IRR-hurdle tiers with promote, and residual split. Among siblings that are single-purpose calculators (calc_irr, calc_npv), this is unmistakably the multi-stage waterfall tool.

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 directive usage: 'use this instead of doing the math yourself', plus a citation requirement (calc.equity_waterfall@1) and an instruction to surface warnings. It also flags that the conventions should be 'confirm[ed] against the operating agreement', which sets the review posture. It stops short of naming an alternative tool or stating when not to use it (e.g. plain IRR-only cases handled by calc_irr).

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

All FactLot 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.