Skip to main content
Glama
Sign In

Worthune Verified Financial Models

by com.worthune
OverviewDiscussionsAdmin

try_household_projection

Read-onlyIdempotent

Run the deterministic multi-year household projection on a document you pass in — income, RMDs, Roth conversions, federal and covered-state tax, expenses, amortization, the tax-grossed-up deficit draw, and net worth per year — optionally with a seeded Monte Carlo. NOTHING IS STORED: no household is created, no id issued, no record kept. Takes any key, a free sandbox key included (worthune.com/sandbox). The response carries every simplification that fired in projection.assumptionsApplied and an evidence record whose hash reproduces on an identical document, so you can show your work. Use list_example_households for a starting shape. For a household that persists — with an id, bulk import, webhooks and drift detection — see create_household.

Input Schema

NameRequiredDescriptionDefault
policyNo
api_keyNoWorthune API key (wk_…); a free sandbox key works
horizonYes
householdYesA household document: { schemaVersion, filingStatus, state?, members[], accounts[], liabilities[], incomes[], expenses[] }. It has no name field and no account numbers by design. Any expense `label` is stripped before anything is computed.
monteCarloNoSimulations are clamped to 500 on this surface, and the clamp is reported back.
assumptionsYesRequired here: this surface has no org profile to fall back on.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed2 schema fields changed
    • addedInput schema / properties / api_key
      Added value: +{
+  "description": "Worthune API key (wk_…); a free sandbox key works",
+  "type": "string"
+}
    • changedInput schema / properties / monteCarlo / description
      Previous value: -"Simulations are clamped to 500 on this keyless surface, and the clamp is reported back."New value: +"Simulations are clamped to 500 on this surface, and the clamp is reported back."
  2. Changed6 schema fields changed
    • addedInput schema / properties / assumptions / additionalProperties
      Added value: +false
    • addedInput schema / properties / horizon / additionalProperties
      Added value: +false
    • changedInput schema / properties / horizon / properties / startYear / maximum
      Previous value: -9007199254740991New value: +2150
    • changedInput schema / properties / horizon / properties / startYear / minimum
      Previous value: --9007199254740991New value: +1900
    • addedInput schema / properties / monteCarlo / additionalProperties
      Added value: +false
    • addedInput schema / properties / policy / additionalProperties
      Added value: +false
  3. Added

TDQS

A4.6/5.0
Behavior5/5

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

Annotations already declare readOnly/idempotent/non-destructive, but the description adds real behavioral context: 'NOTHING IS STORED: no household is created, no id issued, no record kept', auth flexibility ('Takes any key, a free sandbox key included'), the 500-simulation clamp on this surface, and determinism guarantees (evidence hash reproduces on an identical document).

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 purpose and outputs, then constraints, then alternatives — a good information order. It is dense and slightly repetitive (the title already says 'nothing stored', restated as 'NOTHING IS STORED'), but nearly every clause carries load-bearing 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?

For a read-only compute tool with no output schema, the description covers what comes back (projection.assumptionsApplied and an evidence record with a reproducible hash), what the call requires (document, horizon, assumptions, any key), and how it differs from persisted alternatives. Nothing an agent needs to invoke it correctly is missing.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 67% and the schema already documents the api_key sandbox acceptance, the Monte Carlo clamp, the household document shape, and the required assumptions block. The description mostly repeats these at a high level ('optionally with a seeded Monte Carlo') and says nothing about policy.withdrawalOrder or the assumptions fields the schema does not describe, so it adds only marginal parameter meaning.

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?

Specific verb (run a deterministic multi-year projection) plus resource (a household document you pass in), with the computed outputs enumerated. It explicitly distinguishes itself from the persisted sibling: 'For a household that persists — with an id, bulk import, webhooks and drift detection — see create_household.'

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?

Gives explicit when-to-use (sandbox/one-off projection with no storage), names the alternative for persistence (create_household), and points to list_example_households for a starting document shape. Nothing about routing 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 Worthune Verified Financial Models 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