Causal Decision Agent

Overview Schema Source Related Servers Discussions Admin

metalearner

Read-only

Estimate conditional average treatment effects (CATE) using S-, T-, X-, R-, or DR-learners. Compare learner outputs to detect bias and validate causal assumptions for binary treatments.

Instructions

Meta-learner framework for CATE: S-, T-, X-, R-, DR-Learner. Validation: certified parity evidence. Assumptions: Unconfoundedness: Y(d) perp D | X; Overlap: 0 < P(D=1 | X) < 1; For R-Learner / DR-Learner: orthogonality between treatment residual and outcome residual. Pre-conditions: binary treatment (0/1); covariates numeric; categoricals encoded; enough treated AND control to train separate outcome models (T/X/DR-Learner). Failure modes: Large divergence across learner types -> Use sp.compare_metalearners to identify which learner is biased; DR-Learner is safest under model misspecification; S-Learner estimates near zero regardless of true effect -> S-Learner regularization smooths treatment coefficient toward zero; use T/X/DR instead; X-Learner fails when treated group is very small -> X-Learner needs well-identified control-outcome model; fall back to T-Learner or weighted T-Learner. Alternatives: sp.causal_forest, sp.dml, sp.tmle, sp.bcf. Typical minimum N: 500.

Input Schema

TableJSON Schema

Name	Required	Description	Default
`y`	Yes	Outcome variable column name or outcome array.
`treat`	Yes	Binary treatment column (0/1)
`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
`learner`	No	Learner type	dr
`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`	Yes	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

A4.3/5.0

Behavior5/5

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

The description discloses extensive behavioral traits beyond the readOnlyHint=true annotation: assumptions (unconfoundedness, overlap), failure modes per learner (e.g., S-Learner regularizes treatment toward zero, X-Learner fails with small treated group), and validation claims. This goes far beyond the structured annotations.

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 every sentence carries value: it front-loads the core function, then assumptions, pre-conditions, failure modes, and alternatives in a logical order. No filler or redundancy.

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 (10 parameters, multiple learner types) and the existence of an output schema, the description covers assumptions, pre-conditions, failure modes, alternatives, and typical N. It does not explain return format but the output schema covers that. It is remarkably complete for an agent to call 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 the schema already documents all parameters. The description mentions 'binary treatment' and 'covariates numeric' which are also in the schema descriptions, adding little new semantic meaning beyond what the schema provides. Baseline 3 is appropriate.

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

Purpose4/5

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

The description states a specific verb and resource: 'Meta-learner framework for CATE' with explicit learner types (S-, T-, X-, R-, DR-Learner). It lists alternatives but does not explicitly differentiate when to use this vs those siblings, so it is clear but not sharply distinguished.

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?

It provides pre-conditions (binary treatment, numeric covariates, enough treated/control), a typical minimum N, and failure modes that guide when to fall back to alternatives. It lists alternatives (causal_forest, dml, tmle, bcf) but does not explicitly state when to choose metalearner over them, though the pre-conditions imply the intended context.

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

Deploy Server