Causal Decision Agent

Overview Schema Source Related Servers Discussions Admin

multi_treatment

Read-only

Estimates causal effects of multi-valued treatments (3+ levels) using AIPW, returning pairwise contrasts against a reference level.

Instructions

Effects of multi-valued (3+ level) treatments via AIPW. Returns pairwise contrasts versus a reference level. Validation: validated evidence tier (known-truth, reference, external-parity, or Monte Carlo artifact). Assumptions: Generalised unconfoundedness: Y(a) perp T | X for all a; Generalised overlap: 0 < P(T=a | X) < 1 for each arm a; SUTVA across arms. Pre-conditions: treat is integer-valued with >= 2 distinct levels; covariates comprise the confounding set; enough units per treatment arm (>= 50 per arm). Failure modes: Some arm has near-zero propensity in the data -> Violates overlap -- drop that arm or use bounds; Tiny treatment cells (< 30) -> Collapse sparse arms or use regularised multinomial propensity. Alternatives: sp.multi_arm_forest, sp.dml, sp.metalearner. Typical minimum N: 300.

Input Schema

TableJSON Schema

Name	Required	Description	Default
`y`	Yes	Outcome variable column name or outcome array.
`alpha`	No	Significance level for confidence intervals and tests.
`treat`	Yes	Multi-valued treatment (int)
`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
`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`	Yes	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://.
`reference`	No	Reference treatment level (defaults to 0 / smallest)
`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.
`covariates`	Yes	Covariate matrix, DataFrame, or column names.
`n_bootstrap`	No	Number of bootstrap replications.
`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

A4.7/5.0

Behavior5/5

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

Annotations already declare readOnlyHint=true, and the description adds no contradiction. It goes beyond annotations by disclosing statistical assumptions (unconfoundedness, overlap, SUTVA), validation tier, failure modes, and typical minimum N—rich behavioral context for result interpretation.

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?

Despite being long, the description is tightly organised into labelled blocks: Validation, Assumptions, Pre-conditions, Failure modes, Alternatives, and Typical minimum N. Each line carries decision-relevant information 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?

For a 12-parameter tool with an output schema and read-only annotation, the description provides purpose, statistical assumptions, data preconditions, failure handling, alternatives, and sample-size guidance. Combined with the fully described input schema, nothing critical is missing for correct invocation.

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; every parameter already has an individual description. The tool description adds precondition context for treat and covariates, such as integer-valued treatment and confounding set requirements, but does not deeply re-explain individual parameter syntax or interactions.

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 opens with a specific action and scope: estimating effects of multi-valued (3+ level) treatments via AIPW and returning pairwise contrasts versus a reference level. This clearly differentiates the tool from binary treatment effect estimators and other causal inference siblings.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines5/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

It lists explicit pre-conditions (integer-valued treat with >=2 levels, covariates comprising the confounding set, >=50 units per arm) and failure modes that tell the agent when to drop or collapse arms, or use bounds and regularisation. It also names three concrete alternatives, giving clear routing guidance.

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

Deploy Server