Causal Decision Agent

Overview Schema Source Related Servers Discussions Admin

super_learner

Read-only

Fit an ensemble model that combines multiple machine learning algorithms using cross-validation, delivering accurate causal effect estimates for evidence-backed decisions.

Instructions

Fit a Super Learner ensemble. Validation: validated evidence tier (known-truth, reference, external-parity, or Monte Carlo artifact). Assumptions: Unconfoundedness (sequential exchangeability for longitudinal/LTMLE); Positivity / overlap of treatment given history; At least one nuisance (outcome or treatment) is estimated consistently; the targeting step gives double robustness. Pre-conditions: Covariates, treatment, and outcome (for survival/longitudinal variants: time-to-event and time-varying covariates); Enough data to fit a Super Learner / HAL nuisance library. Failure modes: Near-positivity violations create extreme clever-covariate weights -> Truncate weights, restrict the estimand, or report a positivity diagnostic. Alternatives: sp.dml, sp.ipw, sp.g_computation. Typical minimum N: 400.

Input Schema

TableJSON Schema

Name	Required	Description	Default
`X`	Yes	Feature matrix or covariate DataFrame.
`y`	Yes	Outcome variable column name or outcome array.
`task`	No	'regression' or 'classification'.	regression
`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
`library`	No	Candidate learners. If None, uses a default library.
`n_folds`	No	Cross-validation folds.
`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.
`random_state`	No	Random seed or RandomState for reproducible stochastic steps.
`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

A4.2/5.0

Behavior4/5

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

Annotations already declare readOnlyHint=true and openWorldHint=false. The description adds useful statistical behavior context: double robustness, clever-covariate weights, positivity-violation remedies, and truncation guidance. It does not mention side-effect details like caching from as_handle, but that is covered by the schema and the read-only annotation is not contradicted.

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 dense but well-organized with labeled sections: Validation, Assumptions, Pre-conditions, Failure modes, Alternatives, and Typical minimum N. Every sentence contributes substantive information with minimal fluff, though it is longer than strictly necessary.

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?

For a complex 12-parameter estimator, the description supplies essential statistical context: assumptions, preconditions, failure remedies, alternatives, and minimum sample size. An output schema exists, so return-value details do not need to be repeated here. No major operational gap remains.

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 carries the parameter documentation burden. The description only loosely references covariates, treatment, and outcome, and does not elaborate on parameters such as detail, as_handle, library, or n_folds. Baseline 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?

Opens with a specific action, 'Fit a Super Learner ensemble,' naming both the verb and the resource. It also lists alternatives, making it clear this tool is not sp.dml, sp.ipw, or sp.g_computation.

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

Usage Guidelines4/5

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

Provides assumptions, pre-conditions, failure modes, and a typical minimum N of 400, which give strong contextual guidance on when the tool is appropriate. However, it lists alternatives without explicit selection rules such as 'use this when X, otherwise use Y,' so it stops short of full routing guidance.

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

Deploy Server