Causal Decision Agent

Overview Schema Source Related Servers Discussions Admin

test_calibration

Read-only

Assess whether a causal forest's treatment effect estimates are calibrated; a rejected test signals poor heterogeneity calibration, prompting more data or 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

A4/5.0

Behavior4/5

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

Annotations already declare readOnlyHint=true, so the read-only safety profile is covered. The description adds meaningful behavioral context: assumptions (unconfoundedness, overlap, honesty), what a rejection means, and suggested fallback actions, going beyond what the annotations provide.

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 uses labeled sections (Validation, Assumptions, Pre-conditions, Failure modes, Alternatives, Typical minimum N) with no filler. Every sentence contributes actionable context, and the core purpose is front-loaded.

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?

For a complex statistical test, the description covers assumptions, preconditions, failure-mode remediation, alternatives, and a minimum sample size. It appropriately relies on the output schema for return values; the only minor gap is the somewhat vague 'validated evidence tier' phrasing.

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 coverage is 100%, so the input schema already documents all 11 parameters. The description does not add per-parameter syntax or format guidance beyond mentioning assumptions and data requirements, so it stays at the baseline for fully covered schemas.

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 clearly identifies a specific diagnostic: a BLP-of-CATE calibration test with a citation, and states that it tests whether a forest's heterogeneity is well calibrated. It names alternatives like sp.dml, sp.auto_cate, and sp.tmle, but it does not explicitly distinguish itself from closely named siblings such as blp_test or calibration_test.

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 pre-conditions (covariates, treatment, outcome, enough data for an honest forest), failure modes with remediation, and a list of alternatives. It does not give explicit 'use this vs. use that' exclusion rules, but the context is clear enough for an agent to infer when the tool is relevant.

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

Deploy Server