Causal Decision Agent

Overview Schema Source Related Servers Discussions Admin

predict_cate

Read-only

Predict conditional average treatment effects (CATE) for new data using a previously fitted estimator. Provide the fitted result and new covariates to obtain out-of-sample treatment effect estimates.

Instructions

Predict CATE on new (out-of-sample) data. 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
`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
`result`	Yes	Result from ``metalearner()`` containing a fitted estimator.
`new_data`	Yes	New data with the same covariate columns used in estimation.
`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

A4.3/5.0

Behavior4/5

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

Annotations already mark readOnlyHint=true, and the description adds meaningful behavioral context: statistical assumptions (unconfoundedness, overlap, consistent nuisance estimation), failure modes (instability, extrapolation beyond covariate support), and a minimum sample-size guideline. No contradiction with 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 compact, front-loaded with the core purpose, and organized into labeled blocks: assumptions, pre-conditions, failure modes, alternatives, and minimum N. Every sentence contributes useful information without fluff.

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 a rich input schema and an existing output schema, the description supplies the statistical and operational context needed to call the tool correctly: assumptions, data requirements, failure modes, alternative learners, and sample-size guidance. It is complete for an agent deciding when and how to invoke predict_cate.

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 8 parameters. The prose adds little parameter-level detail beyond mapping 'new (out-of-sample) data' to new_data; the baseline 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 opening sentence states the exact operation: 'Predict CATE on new (out-of-sample) data.' This clearly separates it from sibling estimation, summarization, and plotting tools by emphasizing out-of-sample prediction on an already-fitted result.

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 provides explicit preconditions, failure modes with remedies, and an Alternatives list. It does not explicitly say 'call after metalearner()', but the schema's result parameter description supplies that dependency, and no misleading usage guidance is present.

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

Deploy Server