Causal Decision Agent

Overview Schema Source Related Servers Discussions Admin

rate

Read-only

Evaluate treatment effect heterogeneity from a causal forest via rank-average treatment effect, with calibration validation for reliable decisions.

Instructions

Rank-Average Treatment Effect (Yadlowsky et al. 2023). 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 omitted, falls back to the forest's stored training arrays.
`X`	No	If omitted, falls back to the forest's stored training arrays.
`Y`	No	If omitted, falls back to the forest's stored training arrays.
`seed`	No	Ignored; kept for API backwards compatibility.
`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').
`q_grid`	No	Number of quantile grid points used to report the TOC curve. Does not affect the point estimate or SE (those are computed from ranks exactly).
`target`	No	target parameter (str).	AUTOC
`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

A4.5/5.0

Behavior5/5

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

Beyond the readOnlyHint annotation, the description discloses the validation evidence tier, exact assumptions (unconfoundedness, overlap, honesty), failure modes with corrective actions, and a typical minimum sample size. This is rich behavioral context that a read-only hint alone does not provide, and it does not contradict 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.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is dense but every sentence earns its place: method name and citation, validation tier, assumptions, pre-conditions, failure modes with remedies, alternatives, and typical N. It is front-loaded with the core identification and structured in logical blocks, with no filler.

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?

The description covers what the tool does, its assumptions, pre-conditions, failure handling, alternatives, and sample size guidance. Given the presence of an output schema (noted in context signals), the description need not explain return values. It is complete for an agent to decide when to use the tool 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 all parameters are already well-documented in the schema. The description adds some context around the 'forest' parameter via assumptions and failure modes, but does not add syntax-level detail beyond the schema. This meets the baseline for high coverage.

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 clearly states the tool computes the Rank-Average Treatment Effect (RATE) with a citation, identifying the specific method and resource. It also names alternative tools (sp.dml, sp.auto_cate, sp.tmle), distinguishing it from siblings without needing to inspect their schemas.

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 pre-conditions (enough data for an honest forest), failure modes (calibration test rejects, with remedies), and an explicit list of alternatives. However, it does not explicitly state when to choose this tool over the named alternatives (e.g., conditions favoring RATE vs DML), so the guidance is clear but lacks specific exclusion criteria.

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

Deploy Server