Causal Decision Agent

Overview Schema Source Related Servers Discussions Admin

disparity_decompose

Read-only

Decompose a group disparity into direct and mediated components using Jackson & VanderWeele's causal method. Supply data, group, mediator, and outcome to quantify contributors.

Instructions

Jackson & VanderWeele (2018) causal disparity decomposition.

Input Schema

TableJSON Schema

Name	Required	Description	Default
`y`	Yes	Outcome variable column name or outcome array.
`group`	Yes	Group or cohort identifier.
`detail`	No	Payload depth: 'minimal' (~150 tokens) for sub-step calls where only the point estimate is needed; 'standard' (~1K tokens) for diagnostics + coefficient table; 'agent' (~2K tokens, default) adds violations / next_steps / suggested_functions so the LLM can plan its next call without another round-trip.	agent
`mediator`	Yes	mediator parameter (str).
`as_handle`	No	If true, cache the fitted result on the server and return result_id + result_uri alongside the JSON payload so a subsequent tools/call can chain without re-running.
`data_path`	Yes	Absolute path or URL to a data file. Supported: .csv / .tsv / .txt (delimited), .parquet / .pq, .feather / .arrow, .xlsx / .xls, .dta (Stata), .json / .jsonl. Schemes: file://, s3://, gs://, https://.
`result_id`	No	Optional handle to a previously-fitted result (returned by an earlier call when as_handle=true). Tools that operate on a fitted object accept this in place of re-supplying data_path + columns.
`covariates`	No	Covariate matrix, DataFrame, or column names.
`data_columns`	No	Optional column projection. Parquet/Feather/Stata loaders honour this for fast partial reads.
`target_level`	No	Value at which to fix mediator for the "initial" counterfactual.
`data_sample_n`	No	Optional uniform random subsample size (seed=0, deterministic) — useful on huge panels.

Output Schema

TableJSON Schema

Name	Required	Description	Default
No arguments

Schema Changelog

Changes observed during successful MCP inspections.

First observedv0.1.0Sep 15, 2026

TDQS

C2/5.0

Behavior2/5

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

The annotations declare readOnlyHint=true, so there is no contradiction, but the description itself discloses no behavioral traits: no mention of side effects, caching via as_handle, data-loading behavior, or output format. An agent must infer all behavior from the schema rather than from the description.

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

Conciseness3/5

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

The description is admirably short and front-loaded, with no filler or repetition. However, it is terse to the point of under-specification: a citation alone does not convey enough operational information, so the conciseness does not earn a higher score.

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

Completeness1/5

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

For a complex causal decomposition tool with 11 parameters and a large sibling family of decomposition methods, a one-line citation is grossly incomplete. It does not explain what inputs are required, what the result represents, how to interpret the output, or when the Jackson & VanderWeele approach is appropriate.

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

Parameters3/5

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

The input schema provides detailed, self-sufficient descriptions for all parameters, including file formats for data_path, the meaning of detail levels, and the as_handle/result_id chaining mechanism. The description adds no parameter-level meaning beyond the schema, so the baseline of 3 applies.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose2/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description is a noun phrase that essentially restates the tool name ('causal disparity decomposition') and adds a citation, but it does not state what the tool computes, returns, or how it differs from sibling decomposition tools such as mediation_decompose, oaxaca, or yu_elwert_decompose. An agent could guess the general topic but not the specific operation or output.

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

Usage Guidelines1/5

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

There is no guidance on when to use this tool instead of the many decomposition-related siblings, and no prerequisites, exclusions, or context cues are given. The only hint of usage is the 'detail' parameter's description of payload depth, which concerns output verbosity rather than when to select this tool.

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

Deploy Server