Causal Decision Agent

Overview Schema Source Related Servers Discussions Admin

compare_metalearners

Read-only

Compare multiple meta-learners to estimate the average treatment effect under unconfoundedness, using cross-fitting to control overfitting bias.

Instructions

Fit multiple meta-learners and compare their ATE estimates. Assumptions: Unconfoundedness given the covariates; Overlap / positivity across the covariate space; Nuisance functions are estimated consistently; cross-fitting controls overfitting bias. Pre-conditions: Covariates, a treatment indicator, and an outcome for each unit; Enough data to fit flexible nuisance models with sample-splitting / cross-fitting. Failure modes: CATE estimates are unstable or extrapolate beyond the covariate support -> Restrict to the overlap region, increase data, or use a doubly-robust learner (DR-/R-learner). Alternatives: sp.dml, sp.causal_forest, sp.tmle. Typical minimum N: 500.

Input Schema

TableJSON Schema

Name	Required	Description	Default
`y`	Yes	Outcome variable.
`treat`	Yes	Binary treatment variable (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
`learners`	No	Which learners to compare. Default: all five ('s','t','x','r','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 / effect modifier variables.
`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

Behavior4/5

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

Annotations already declare the tool read-only)Skip, and the description adds valuable behavioral context: statistical assumptions (unconfoundedness, overlap, consistent nuisance functions), failure modes (unstable or extrapolating CATE estimates), and practical guidance (minimum N=500). This goes 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 well-structured with labeled sections (Assumptions, Pre-conditions, Failure modes, Alternatives, Typical minimum N). Each sentence carries distinct, non-redundant information, and the most critical contrasts (alternatives) are included without waste.

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 tool that fits multiple meta-learners, the description covers assumptions, pre-conditions, failure modes, alternatives, and minimum sample size. An output schema exists, so return values are already handled. The agent has everything needed to decide when to call and what to expect.

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 baseline is 3. The description does not add parameter-specific meaning beyond the schema, but it implicitly signals the role of covariates, treatment, and outcome via its pre-conditions and assumptions.

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 ('fit') and resource ('multiple meta-learners' and 'ATE estimates'), making the tool's purpose immediately clear. It also names alternatives (sp.dml, sp.causal_forest, sp.tmle), which helps distinguish it from sibling causal-inference tools.

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?

The description explicitly lists alternatives and provides pre-conditions and assumptions that define when the tool is appropriate. However, it does not give explicit criteria for choosing among the named alternatives, leaving some selection inference to the agent.

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

Deploy Server