Causal Decision Agent

Overview Schema Source Related Servers Discussions Admin

calibration_test

Read-only

Checks whether a causal forest's treatment-effect heterogeneity is well calibrated, so you can decide whether to trust the model or switch to a doubly-robust learner.

Instructions

BLP-of-CATE calibration test (Chernozhukov-Demirer-Duflo-Fernandez-Val 2020). 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	If not given, the forest's stored training arrays are used.
`X`	No	If not given, the forest's stored training arrays are used.
`Y`	No	If not given, the forest's stored training arrays are used.
`alpha`	No	Significance level for reported CIs.
`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.

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

A3.9/5.0

Behavior4/5

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

Annotations already declare readOnlyHint=true and openWorldHint=false, and the description goes beyond this by detailing validation tiers, assumptions, failure behavior (rejection), and typical minimum N. This adds meaningful behavioral context without contradicting the annotations.

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 structured with labeled sections (Validation, Assumptions, Pre-conditions, Failure modes, Alternatives, Typical minimum N), making it scannable and information-dense. It is not overly verbose and gets to the point quickly with the method name up front.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the tool's complexity, the presence of an output schema, and readOnly annotation, the description covers the essential statistical context (assumptions, failure modes, sample size guidance). It does not explain generic parameters like as_handle or data_path, but those are handled by the schema and are common across tools.

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 mentions 'forest' and covariates/treatment/outcome, which slightly reinforces the schema's param descriptions, but it does not add new meaning to any individual parameter beyond what the schema already states.

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?

Description states a specific verb and resource ('BLP-of-CATE calibration test') and references the 2020 paper, making the core function clear. However, it does not explicitly distinguish itself from close sibling tools like 'test_calibration' or 'blp_test', leaving some ambiguity for tool selection.

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 alternatives, which gives an agent strong context on when to use the tool and how to react to output. It lacks an explicit 'use this when...' statement or exclusions, but the pre-conditions and mass of guidance make usage conditions reasonably clear.

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

Deploy Server