Intangible Asset Valuation

Uncertainty & Sensitivity

valuation_simulation

Read-onlyIdempotent

Quantify uncertainty around intangible asset valuations using Monte Carlo simulations, sensitivity rankings, decision-tree expected values, and one-at-a-time parameter tests.

Instructions

Uncertainty analysis: Monte Carlo valuation, Monte Carlo sensitivity ranking, decision-tree expected values, and one-at-a-time sensitivity analysis. Method selects the formula. Use to quantify and stress the uncertainty around a point valuation; monte_carlo simulates all listed inputs, monte_carlo_sensitivity ranks the drivers. For a single deterministic point value use the relevant valuation tool; sensitivity_analysis varies one parameter of a core function only. Per method: monte_carlo needs input_distributions (optional: iterations, seed); monte_carlo_sensitivity needs base_params + distributions (optional: iterations, seed); decision_tree needs tree; sensitivity_analysis needs function_name + parameter_name + parameter_range + fixed_parameters. monte_carlo_sensitivity requires iterations between 1000 and 100000. Only method is required; other parameters are method-dependent, so supply those named for the selected method and omit the rest (documented defaults apply where defined). Pure arithmetic: no I/O and no external calls, and numeric results are returned rounded to 2 decimals. Parameters belonging to other methods of this tool are accepted and ignored. Supplying an unknown method, or leaving unset a parameter that the chosen method requires, returns an error instead of a value.

Input Schema

TableJSON Schema

Name	Required	Description
`seed`	No	Random seed for reproducible simulations.
`tree`	No	Decision tree {"nodes": [...], "edges": [...]}; node types decision, chance, terminal.
`method`	Yes	Formula to apply. Options: monte_carlo = Simulate all listed inputs, sum-based valuation.; monte_carlo_sensitivity = Rank parameters by their impact on the valuation.; decision_tree = Backward induction over a decision tree.; sensitivity_analysis = One-at-a-time sensitivity of a core function.
`iterations`	No	Simulation iterations; monte_carlo_sensitivity requires 1000-100000.
`base_params`	No	Base values for all parameters, including those held fixed.
`distributions`	No	Map of parameter name to {distribution, params} for the simulated inputs.
`function_name`	No	Core function to vary, e.g. "present_value", "capm_discount_rate", "wacc".
`parameter_name`	No	Name of the parameter to vary.
`parameter_range`	No	Values to test for the varied parameter.
`fixed_parameters`	No	Values for all other parameters, held constant.
`input_distributions`	No	Inputs to simulate, each {name, distribution, params}; distribution is normal (mean, std), uniform (low, high) or triangular (low, high, mode).

Output Schema

TableJSON Schema

Name	Required	Description
`error`	No	Error message when the call fails.
`steps`	No	Intermediate calculation steps for traceability (one string per step).
`value`	Yes	Computed valuation, rate, or metric.
`method`	No	Formula / method name that produced the result.
`assumptions`	No	Modelling assumptions applied (list of strings or key/value object).
`formula_reference`	No	Mathematical formula or reference applied.

Schema Changelog

Changes observed during successful MCP inspections.

Changed2 schema fields changedv0.1.4Sep 30, 2026

changedOutput schema / properties / steps / description

Previous value: -"Intermediate calculation steps for traceability."New value: +"Intermediate calculation steps for traceability (one string per step)."

removedOutput schema / properties / steps / items / type
```
Removed value: -"object"
```

First observedv0.1.0Sep 30, 2026

TDQS

A4.8/5.0

Behavior5/5

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

Annotations already declare a safe, idempotent, non-destructive read, and the description adds substantial extra behavior: pure arithmetic with no I/O or external calls, results rounded to 2 decimals, parameters for other methods are accepted and ignored, and that an unknown method or a missing required parameter returns an error instead of a value.

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?

It is front-loaded with the purpose, then alternatives, then per-method parameter requirements, then behavioral notes. It is long but dense, with only minor redundancy ('uncertainty analysis' restated as 'quantify and stress the uncertainty').

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?

With an output schema present, return-value details are unnecessary, and the description still covers the hard parts: conditional per-method parameters, defaults, iteration bounds, error semantics, and the ignored-extra-parameter behavior. 11 parameters with only one required are adequately disambiguated.

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 coverage is 100%, so the schema documents each field individually and the baseline would be 3. The description goes beyond this by mapping which parameters are required per method and by clarifying that only 'method' is required while the rest are method-dependent and should be supplied/omitted accordingly, which the schema cannot express on its own.

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 names the resource (uncertainty analysis) and enumerates the four concrete methods it computes (Monte Carlo valuation, Monte Carlo sensitivity ranking, decision-tree expected values, one-at-a-time sensitivity), with method selecting the formula. It also differentiates itself from siblings by stating that a single deterministic point value belongs to 'the relevant valuation tool' rather than here.

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?

It gives explicit routing: use this to quantify/stress uncertainty around a point valuation; use a valuation tool for a deterministic point value; use sensitivity_analysis only to vary one parameter of a core function. It further states per-method requirements (which parameters each method needs) and the 1000-100000 iteration bound for monte_carlo_sensitivity.

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

Deploy Server