Causal Decision Agent

Overview Schema Source Related Servers Discussions Admin

decompose

Read-only

Decompose outcome gaps between groups using validated methods like Oaxaca-Blinder, RIF, or Machado-Mata. Receive diagnostics and actionable next steps to address violations and plan analysis.

Instructions

Unified entry point for all decomposition methods. Validation: certified parity evidence. Assumptions: Overlapping support of covariates across groups (reweighting / RIF methods are invalid outside overlap); Linearity assumption holds for Oaxaca-Blinder-type decompositions; non-linear methods (FFL/DFL/Machado-Mata) relax this; Conditional independence of group membership for causal interpretation (otherwise: descriptive decomposition only). Pre-conditions: Data contains a binary or categorical group indicator with both groups represented; Outcome and covariates are numeric (or properly encoded) and finite; Sample sizes per group are large enough to estimate group-specific moments (rule of thumb: each group >= 100). Failure modes: Trimming warning at common-support boundaries -> Inspect propensity-score support; restrict the analysis sample or use bounds; RIF coefficients explode at distribution tails -> Use higher-bandwidth kernel density, restrict quantile range, or switch to FFL. Alternatives: sp.dfl_decompose, sp.ffl_decompose, sp.oaxaca, sp.rif_decomposition. Typical minimum N: 200.

Input Schema

TableJSON Schema

Name	Required	Description	Default
`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
`method`	Yes	One of the methods listed in ``available_methods()``. Aliases are supported (e.g. 'mm' -> 'machado_mata').
`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`	No	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

A4.7/5.0

Behavior5/5

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

Annotations declare readOnlyHint=true and openWorldHint=false, and the description adds substantial behavioral context beyond those: assumptions about overlap and linearity, pre-conditions on group sizes, failure modes with remediation steps, and a typical minimum N of 200. This goes well beyond the structured annotation data.

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

Conciseness5/5

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

The description is dense but well-structured with labeled sections: Validation, Assumptions, Pre-conditions, Failure modes, Alternatives, and Typical minimum N. Every sentence adds actionable information, and the core purpose is front-loaded in the first sentence.

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 tool's complexity, the description covers assumptions, preconditions, failure modes, alternatives, and sample-size guidance. An output schema exists, so return-value details are not required. The description provides everything an agent needs to decide whether and how to invoke decompose.

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?

Schema description coverage is 100%, so the schema already documents all 7 parameters including method aliases, detail levels, and data_path formats. The description does not add parameter-level meaning beyond the schema, so the baseline score 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 clearly identifies this as the unified entry point for all decomposition methods, which is a specific resource and scope. It distinguishes itself from the specialized sibling tools by naming them in the Alternatives section, so an agent can tell it apart from sp.dfl_decompose, sp.ffl_decompose, sp.oaxaca, and sp.rif_decomposition.

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?

The description provides explicit when-to-use guidance via the 'Unified entry point' framing and lists specific alternatives. It also includes conditional guidance in failure modes, e.g., 'RIF coefficients explode at distribution tails -> switch to FFL,' and assumption-based exclusions such as reweighting/RIF being invalid outside overlap.

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

Deploy Server