Causal Decision Agent

Overview Schema Source Related Servers Discussions Admin

cardinality_match

Read-only

Maximizes matched treatment-control pairs under validated evidence tiers, enforcing covariate overlap and unconfoundedness for reliable causal effect estimation.

Instructions

Cardinality matching -- maximise the number of matched pairs subject Validation: validated evidence tier (known-truth, reference, external-parity, or Monte Carlo artifact). Assumptions: Unconfoundedness: treatment is as-good-as-random given the measured covariates; Overlap / common support: every unit has a non-degenerate probability of each treatment; The covariate set blocks all back-door paths. Pre-conditions: Pre-treatment covariates measured for treated and control units; A binary (or low-cardinality) treatment indicator; Sufficient covariate overlap between treatment arms. Failure modes: Poor overlap -- extreme propensity scores or few acceptable matches -> Trim or restrict to the common-support region and report the discarded units; Covariate imbalance remains after matching/weighting -> Re-specify the balancing model (CBPS, entropy balancing) and re-check standardized mean differences. Alternatives: sp.propensity_score, sp.cbps, sp.ebalance, sp.dml. Typical minimum N: 200.

Input Schema

TableJSON Schema

Name	Required	Description	Default
`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
`outcome`	Yes	Outcome variable column name or outcome array.
`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://.
`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.
`treatment`	Yes	Treatment indicator, treatment variable, or treatment array.
`covariates`	Yes	Covariate matrix, DataFrame, or column names.
`time_limit`	No	time_limit parameter (float).
`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.
`smd_tolerance`	No	smd_tolerance parameter (float).

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

B3.2/5.0

Behavior4/5

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

Annotations already declare readOnlyHint=true. The description adds meaningful behavioral context: assumptions, pre-conditions, failure modes with concrete remedies (trim/restrict common support, re-specify balancing model), and a typical minimum N. It also references a validation tier, which hints at output behavior beyond what annotations alone provide. No contradiction exists.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness3/5

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), which helps navigation. However, it is dense, the opening sentence is grammatically broken ('subject Validation:'), and the 'Validation' line is cryptic and not clearly valuable. It is structured but not as concise or well front-loaded as it could be.

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

Completeness3/5

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

Given the rich input schema and presence of an output schema, the description need not explain return values. It covers assumptions, preconditions, failure modes, alternatives, and sample-size guidance. However, it does not explain what makes cardinality matching different from sibling methods, so an agent lacks enough contextual information to decide when this tool is the right choice.

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 schema already documents all parameters. The description adds little about parameters beyond reiterating conditions like 'pre-treatment covariates measured for treated and control units' and 'binary (or low-cardinality) treatment indicator', which loosely map to covariates and treatment but do not meaningfully enhance parameter-level understanding.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose3/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description identifies cardinality matching as 'maximise the number of matched pairs' but does not state in a clear verb+resource form what the tool does. It distinguishes itself from some matching alternatives by name, but the opening sentence is incomplete and the method is not explicitly defined, leaving the agent to infer the core operation.

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

Usage Guidelines3/5

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

Pre-conditions (pre-treatment covariates, binary/low-cardinality treatment, overlap) and alternatives (propensity_score, cbps, ebalance, dml) imply when the tool may be used, but no explicit guidance is given for choosing cardinality_match over those alternatives. It does not say when this tool should be avoided or which sibling is preferable in a given scenario.

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

Deploy Server