Skip to main content
Glama
RetireGolden

RetireGolden MCP

Official
by RetireGolden

build_plan

Construct or update a retirement plan by providing household financial data, policy choices, and optional assumptions, or by importing a full plan JSON.

Instructions

Educational decision-support only — not tax, legal, or financial advice. Do not prescribe securities actions. Build or replace the in-memory plan from typed household/policy params or full plan JSON.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
planNoFull RetireGolden plan JSON (validated by the engine)
policyNoTyped policy params: claim_ages[], optional conversion_bracket/conversion_years, withdrawal ordering
householdNoTyped household params: filing, REQUIRED 2-letter state, persons[] (retired — a non-zero wage is a hard error), taxable/basis, spending, horizon, growth rates, IRMAA lookback MAGIs, heir rate
startYearNo
conversionNoOptional manual Roth conversion schedule (overrides bracket-fill conversions)
mcpVersionNoProvenance only: the `mcpVersion` sibling from an export_plan response, accepted so a whole export can be spread straight back into build_plan (including the null export_plan emits when the version is unresolvable). Recorded, never warned on — for a full plan document the document itself is the model.
assumptionsNoOptional overrides for default modeling assumptions (inflation, returns, SS COLA, state, taxes, qualified ratio, dob month-day, sex). Defaults follow the engine (~2.5% inflation, SS COLA tracking inflation, and the resident state's own modeled income tax — set stateEffectiveTaxPct above 0 only to override that with a flat rate); household state is a REQUIRED input, not an assumption. Set explicit values to override; omitted fields keep the engine defaults.
conventionsNo
engineVersionNoProvenance only: the `engineVersion` sibling from an export_plan response, i.e. the @retiregolden/engine build that exported the supplied `plan`. Differing from the running engine adds a caveat (defaults and modeling semantics can move between engine versions) and NOTHING else — the document is still imported. This is the version skew that can actually occur between two builds that can exchange documents at all. Accepts null, which is what export_plan emits when it cannot resolve the installed version; null is treated as 'unknown' and warns on nothing.
schemaVersionNoProvenance only: the `schemaVersion` sibling from an export_plan response. A value differing from this build's version adds a caveat and NOTHING else — the document is still imported. Note this is your CLAIM about the document; the version the engine actually gates on is the `schemaVersion` field inside the document itself. Omit it and no caveat is emitted.
Behavior3/5

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

With no annotations, the description carries full burden. It discloses that the tool builds or replaces an in-memory plan and mentions specific constraints (e.g., non-zero wage causes hard error, state requirement). However, it does not detail side effects like mutation of persistent state, idempotency, or error behavior beyond the wage example. Sufficient but not exhaustive.

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?

The description is brief (three sentences) and front-loaded with the core action. The disclaimer is minor. It efficiently conveys the main purpose without redundancy. However, the disclaimer could be integrated or placed after the action for better structure.

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

Completeness2/5

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

The description omits information about the return value or effect on the system. With no output schema and a complex set of parameters, the agent needs to know what the tool returns or how the in-memory plan is affected. It also does not mention relation to sibling tools like validate_plan or run_projection, leaving gaps in understanding the workflow.

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 description coverage is 80%, but the description adds significant value by explaining contextual details like required state on typed path, override mechanisms (assumptions.state), and hard error on non-zero wage. It clarifies parameter relationships and edge cases beyond the schema's own descriptions.

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?

The description clearly states the tool's action: 'Build or replace the in-memory plan from typed household/policy params or full plan JSON.' It specifies the verb 'build or replace' and the resource 'in-memory plan', distinguishing it from siblings like validate_plan or run_projection, which have different purposes.

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

Usage Guidelines2/5

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

The description lacks guidance on when to use this tool versus alternatives. It only includes a disclaimer about educational use, but does not specify scenarios, prerequisites, or when not to use it. No explicit when-to-use or when-not-to-use advice is provided.

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

Install Server

Other Tools

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/RetireGolden/RetireGolden-MCP'

If you have feedback or need assistance with the MCP directory API, please join our Discord server