Skip to main content
Glama
vosesoftware

ModelRisk MCP

Official
by vosesoftware

build_model_from_brief

Convert a deterministic workbook into a Monte Carlo model in one atomic pass. Wraps outputs with VoseOutput and replaces uncertain inputs with distributions from a brief, with validation and rollback.

Instructions

ModelRisk: Turn a deterministic workbook into a simulation-ready Monte Carlo model in one atomic, reversible pass. Given the output cells to track and the uncertain inputs to add (each with a Vose distribution family + parameters you choose from the brief), it wraps the outputs with VoseOutput, replaces the input cells with VoseInput-wrapped distributions, optionally runs a validating simulation, and returns the headline percentiles. Every write goes through the audit-logged safe-write path and is tracked in a change-set: if any step fails, the ENTIRE build is rolled back so the workbook is never left half-converted. Defaults to dry_run=True. This end-to-end build+simulate is exactly what an advisory agent cannot do.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
runNoRun a validating simulation after building. Default True.
seedNo
sheetYesSheet holding the cells.
inputsYesUncertain inputs to create, each: {'cell': 'B4', 'input_name': 'Demand', 'function_name': 'VoseModPERT', 'parameters': [{'value': 100}, {'value': 150}, {'value': 250}]}.
dry_runNoPreview the planned build without writing. Default True.
outputsNoOutput cells to wrap: [{'cell': 'B12', 'output_name': 'NPV'}]. Omit if outputs are already wrapped.
samplesNo
workbookYesWorkbook file name.

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault
noteYes
stepsYesOrdered, human-readable log of the build.
dry_runYes
headlineNoPer-output headline stats (mean/P10/P50/P90) from the validating run.
workbookYes
simulatedNo
correlatedNo
rolled_backNo
inputs_builtNo
change_set_sizeYesNumber of cells written (0 if dry_run).
outputs_wrappedNo
Behavior5/5

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

With no annotations, the description fully discloses behavior: atomic and reversible pass, audit-logged safe-write path, change-set tracking, rollback on failure, default dry_run=True, and returns headline percentiles. This is comprehensive transparency.

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 three sentences, dense with information, but front-loaded with the main action. Each sentence adds value, though slightly verbose. It efficiently conveys key details without unnecessary fluff.

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?

Given the complexity (8 parameters, no annotations, output schema exists), the description covers purpose, usage guidelines, behavioral nuances, and parameter hints comprehensively. It leaves little ambiguity for an AI agent.

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?

The input schema covers 75% of parameters with descriptions, and the tool description adds context for inputs (Vose distribution families) and provides example structures. This enhances understanding beyond the schema alone.

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 converts a deterministic workbook into a Monte Carlo model, using specific verbs like 'turn', 'wrap', 'replace', and 'run'. It distinguishes itself from siblings by emphasizing it's an end-to-end build that an advisory agent cannot perform.

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?

The description specifies the inputs needed (output cells and uncertain inputs) and the actions performed, implying when to use this tool. However, it does not explicitly state when not to use or mention alternative tools, though it contrasts with advisor limitations.

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/vosesoftware/modelrisk-mcp'

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