Skip to main content
Glama
vosesoftware

ModelRisk MCP

Official
by vosesoftware

decompose_uncertainty

Split a model output's uncertainty into epistemic (reducible with more data) and aleatory (natural variability) components using two simulation runs, to identify whether to collect more data or manage variability.

Instructions

ModelRisk: Split an output's uncertainty into EPISTEMIC (parameter / knowledge uncertainty — reducible with more data) and ALEATORY (natural variability — irreducible), via the law of total variance. ModelRisk has no two-dimensional-simulation worksheet function, so this approximates it from two runs you provide as two outputs: total_output from a full run (everything varying), and conditional_output from a run with the epistemic/parameter inputs FROZEN at point estimates (only natural variability left). Epistemic variance = total - aleatory. Tells you whether collecting more data (cuts epistemic) or hedging variability (aleatory) is the lever.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
max_nNoMax samples to read (default 100 000).
total_outputYesOutput name from the full run (all inputs varying).
workbook_nameNoWorkbook name. Omit for the active workbook.
conditional_outputYesOutput name from the run with epistemic inputs frozen.

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault
total_stdevYes
total_outputYes
aleatory_shareYesAleatory fraction of total variance (0-1).
aleatory_stdevYes
interpretationYesWhich uncertainty dominates and what reduces it.
total_varianceYes
epistemic_shareYesEpistemic fraction of total variance (0-1).
epistemic_stdevYessqrt(max(epistemic_variance, 0)).
aleatory_varianceYesVariability remaining when epistemic (parameter) inputs are frozen.
conditional_outputYes
epistemic_varianceYestotal - aleatory; the part driven by parameter uncertainty.
Behavior4/5

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

No annotations are provided, so the description carries full burden. It discloses that the tool approximates a two-dimensional simulation via law of total variance and requires specific run configurations. It explains epistemic vs. aleatory uncertainty. It does not mention side effects, error conditions, or performance impacts, but for a read-like analytical tool, the disclosure is adequate.

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 a single paragraph that front-loads the main purpose in the first sentence. It explains the method, requirements, and outcome efficiently without redundancy. Slightly dense but no wasted words, earning a score of 4.

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?

The description covers the conceptual input requirements and the decision insight but does not mention the output format or any return value. Despite 'Has output schema: true', the description would benefit from a brief note on what the tool returns (e.g., variance components). Otherwise, the agent might be unclear on the result structure.

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 100%, but the description adds meaning by explaining the purpose of 'total_output' and 'conditional_output' beyond the schema's bare name. It clarifies that 'total_output' comes from a full run and 'conditional_output' from a frozen run. This extra context enhances parameter understanding.

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 action 'Split an output's uncertainty into EPISTEMIC and ALEATORY' using 'law of total variance', with a specific verb and resource. It distinguishes this tool from siblings by its unique decomposition purpose, which is not duplicated by other listed tools.

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 provides clear context for when to use: requires two specific outputs from two runs (full run and frozen-epistemic run). It explains the approximating nature and the decision insight it provides (whether to collect more data or hedge variability). However, it does not explicitly state when not to use or list alternative tools, missing some explicit exclusion criteria.

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