Causal Decision Agent

Overview Schema Source Related Servers Discussions Admin

subgroup_decompose

Read-only

Decompose an inequality index into between-group and within-group components to identify which subgroups drive disparities, with certified parity evidence for validation.

Instructions

Subgroup decomposition (between / within) of an inequality index. Validation: certified parity evidence.

Input Schema

TableJSON Schema

Name	Required	Description	Default
`y`	Yes	Outcome variable column name or outcome array.
`by`	Yes	by parameter (str).
`eps`	No	eps parameter (float).
`alpha`	No	Significance level for confidence intervals and tests.
`index`	No	index parameter (str).	theil_t
`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
`weights`	No	Observation weights.
`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.
`data_columns`	No	Optional column projection. Parquet/Feather/Stata loaders honour this for fast partial reads.
`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

C2.9/5.0

Behavior2/5

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

Annotations already declare readOnlyHint=true, so the safety profile is known. The description adds a cryptic 'Validation: certified parity evidence' note, which hints at a validation behavior but does not explain what it does, what it produces, or how it affects the output. No meaningful behavioral context is given beyond what annotations already provide.

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 compact and front-loaded, with the core function stated first. However, the second sentence about 'certified parity evidence' is vague and does not clearly contribute to understanding the tool's behavior, slightly reducing clarity.

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?

Given the tool has 12 parameterspell an output schema, and sits among many similar decomposition sibling tools, the description is incomplete. It lacks high-level context about when to use it, what outputs to expect, or any assumptions on input data. The schema carries the entire burden, and the description does not help an agent understand the tool's role in an analysis pipeline.

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 has 100% description coverage, with each parameter (including the 'detail' enum) already documented in detail. The description adds no parameter-specific meaning, so the baseline of 3 is appropriate.

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 states a specific verb ('decomposition') and a specific resource ('inequality index') and specifies the between/within split, which clearly distinguishes it from other decomposition tools like disparity_decompose or mediation_decompose. The purpose is unambiguous.

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?

The description provides no guidance on when to use this tool versus alternatives, no prerequisites, no exclusions. It does not mention any context in which subgroup_decompose should be preferred over other decomposition functions among the dozens of siblings.

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

Deploy Server