Causal Decision Agent

Overview Schema Source Related Servers Discussions Admin

average_treatment_effect

Read-only

Aggregate CATE predictions into ATE/ATT/ATC/ATO estimates, with calibration diagnostics and validation, to support evidence-based treatment decisions.

Instructions

Aggregate CATE predictions into ATE/ATT/ATC/ATO targets. Validation: validated evidence tier (known-truth, reference, external-parity, or Monte Carlo artifact). Assumptions: Unconfoundedness given the covariates; Overlap / positivity; Honesty: separate subsamples are used to choose splits and to estimate effects. Pre-conditions: Covariates, treatment, and outcome with enough data to grow an honest forest. Failure modes: Calibration test rejects -- the forest's heterogeneity is not well calibrated -> Increase the sample / number of trees, or fall back to a doubly-robust learner. Alternatives: sp.dml, sp.auto_cate, sp.tmle. Typical minimum N: 1000.

Input Schema

TableJSON Schema

Name	Required	Description	Default
`T`	No	T parameter (Optional[np.ndarray]).
`X`	No	Feature matrix or covariate DataFrame.
`clip`	No	Propensity scores are clipped to ``[clip, 1-clip]`` before the inverse-propensity term to stabilise the score under near-overlap violations.
`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
`forest`	Yes	forest parameter ('CausalForest').
`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.
`target_sample`	No	target_sample parameter (str).	all

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

A4.5/5.0

Behavior5/5

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

Annotations include readOnlyHint=true, so the description does not need to restate that. It adds substantial behavioral context: assumptions (unconfoundedness, overlap, honesty), failure modes (calibration test rejects) with remediation steps, and validation tier. This exceeds the bar set by 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 structured with labeled sections (validation, assumptions, pre-conditions, failure modes, alternatives, typical N), is front-loaded with the core purpose, and every sentence contributes useful information without 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?

For a complex tool with 12 parameters and an output schema, the description covers purpose, assumptions, pre-conditions, failure modes, alternatives, and sample size guidance. An agent has sufficient information to decide when to call it and how to handle common issues.

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 12 parameters are already documented in the schema. The description does not add parameter-specific details beyond what the schema provides, so the 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?

States a specific verb (aggregate) and resource (CATE predictions into ATE/ATT/ATC/ATO targets), and distinguishes from siblings by naming alternatives. The purpose is unambiguous and agent-actionable.

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 context: pre-conditions (requires a forest) and typical minimum N, plus alternatives. It does not explicitly state when NOT to use this tool versus the alternatives, but the pre-condition implies you need a CausalForest, which is a clear usage signal.

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

Deploy Server