Causal Decision Agent

Overview Schema Source Related Servers Discussions Admin

mediation_decompose

Read-only

Decompose a treatment's total effect into direct and indirect effects via a mediator using validated linear nested models. Provides bootstrap or analytical inference and actionable verdicts for causal decisions.

Instructions

Linear nested-models mediation decomposition (VanderWeele 2014 Validation: validated evidence tier (known-truth, reference, external-parity, or Monte Carlo artifact).

Input Schema

TableJSON Schema

Name	Required	Description	Default
`y`	Yes	Outcome variable column name or outcome array.
`seed`	No	Random seed for reproducible stochastic steps.
`alpha`	No	Significance level for confidence intervals and tests.
`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
`n_boot`	No	Number of bootstrap replications.
`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://.
`inference`	No	inference parameter (str).	analytical
`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.
`treatment`	Yes	Treatment indicator, treatment variable, or treatment array.
`covariates`	No	Covariate matrix, DataFrame, or column names.
`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

C2/5.0

Behavior2/5

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

Annotations declare readOnlyHint=true, which covers safety, but the description adds no behavioral context—no mention of what the output contains, whether it requires specific data formats, or any side effects. It merely mentions a 'Validation' tier that seems out of place.

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

Conciseness2/5

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

The description is short but poorly structured: it reads like a cut-off sentence and includes an irrelevant validation phrase. It is not concise in a useful way—it omits essential information while including a confusing fragment.

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 14 parameters, an output schema, and a long list of related decomposition tools, the description fails to explain the tool's purpose, use cases, or how it differs from siblings. It is far from complete for an agent to decide correctly.

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 all parameters are documented. The description adds nothing beyond that, but the baseline of 3 is appropriate given the schema already carries the semantic weight.

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 fragment: 'Linear nested-models mediation decomposition (VanderWeele 2014' followed by an unrelated validation note. It names the method family but never states what the tool actually does (e.g., decomposes total effect into direct/indirect components). It is not a tautology, but it is too vague and incomplete to guide an agent.

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 versus the many mediation siblings (mediation, mediate_interventional, decompose, disparity_decompose). No conditions, exclusions, or alternatives are mentioned.

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

Deploy Server