Worthune Verified Financial Models

project_household

Idempotent

Run the deterministic multi-year projection on a stored household — income, RMDs, federal + covered state tax, expenses, amortization, cash flow, net worth per year — optionally with seeded Monte Carlo (same seed, same result). Assumptions: pass your own, pin a profile by id+version, or omit both for the labeled illustrative default; the response always names its assumptionsSource. Every simplification that fired is listed in projection.assumptionsApplied — show your work.

Input Schema

TableJSON Schema

Name	Required	Description
`id`	Yes
`policy`	No	Same shape as try_household_projection; applies to the deterministic run and every Monte Carlo path, and is hashed into the record.
`api_key`	No	Worthune API key (wk_…)
`horizon`	Yes
`profile`	No
`monteCarlo`	No
`assumptions`	No

Schema Changelog

Changes observed during successful MCP inspections.

Changed7 schema fields changedSep 6, 2026

addedInput schema / properties / assumptions / additionalProperties
```
Added value: +false
```
addedInput schema / properties / assumptions / properties / socialSecurityCola
```
Added value: +{
+  "type": "number"
+}
```
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

Added value: +{
+  "additionalProperties": false,
+  "description": "Same shape as try_household_projection; applies to the deterministic run and every Monte Carlo path, and is hashed into the record.",
+  "properties": {
+    "rothConversions": {
+      "items": {
+        "properties": {
+          "amountUsd": {
+            "type": "number"
+          },
+          "year": {
+            "maximum": 9007199254740991,
+            "minimum": -9007199254740991,
+            "type": "integer"
+          }
+        },
+        "required": [
+          "year",
+          "amountUsd"
+        ],
+        "type": "object"
+      },
+      "type": "array"
+    },
+    "withdrawalOrder": {
+      "items": {
+        "type": "string"
+      },
+      "type": "array"
+    }
+  },
+  "type": "object"
+}

Changed1 schema field changedAug 28, 2026
- addedInput schema / properties / monteCarlo / properties / longevity
```
Added value: +{
+  "type": "boolean"
+}
```

Changed1 schema field changedAug 27, 2026

addedInput schema / properties / assumptions / properties / returnsByWrapper

Added value: +{
+  "additionalProperties": {
+    "type": "number"
+  },
+  "propertyNames": {
+    "type": "string"
+  },
+  "type": "object"
+}

AddedAug 27, 2026

TDQS

A3.5/5.0

Behavior4/5

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

The description adds meaningful behavioral context beyond the annotations: it discloses determinism, seeded Monte Carlo reproducibility ('same seed, same result'), and that the response always names assumptionsSource and lists fired simplifications in projection.assumptionsApplied. These details align with idempotentHint and provide transparency the annotations alone do not.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is two sentences with no fluff. It front-loads the core action and output components, then adds assumption-selection guidance and behavioral transparency. Every clause earns its place, including the compact 'show your work' closer.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness3/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a tool with seven parameters, nested objects, low schema coverage, and no output schema, the description provides a good high-level picture of outputs and transparency guarantees. However, it leaves several important invocation details—especially Monte Carlo sub-parameters, api_key handling, and horizon constraints—to the schema, making it adequate but not fully complete.

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

Parameters2/5

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

Schema description coverage is only 29%, so the description needs to compensate for under-documented parameters. It adds useful semantics for assumptions/profile modes but says nothing about the required id and horizon parameters, and it does not explain the monteCarlo object's sub-fields or policy details beyond what the schema already states.

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 description names a specific verb ('Run'), a specific resource ('stored household'), and enumerates the projection outputs, making the tool's purpose clear. It does not explicitly distinguish itself from siblings like try_household_projection, though the 'stored household' phrasing hints at the difference.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines3/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description gives clear context for how to invoke the tool: pass assumptions, pin a profile by id+version, or use the default, and optionally enable seeded Monte Carlo. However, it does not explicitly state when to prefer this tool over alternatives such as try_household_projection or run_model, nor does it list when-not-to-use conditions.

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 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.

Resources

Need Help?