Skip to main content
Glama
vikranthviki

Causal Decision Agent

by vikranthviki
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Python
Local

psm

Read-only

Match treated and control units on propensity scores to reduce confounding and estimate causal treatment effects from observational data.

Instructions

Propensity-score matching -- article alias for :func:match Validation: certified parity evidence. 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
NameRequiredDescriptionDefault
XYesFeature matrix or covariate DataFrame.
dYesd parameter (str).
yYesOutcome variable column name or outcome array.
detailNoPayload 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
methodNoEstimator or algorithm variant to use.nn
as_handleNoIf 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_pathYesAbsolute 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_idNoOptional 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_columnsNoOptional column projection. Parquet/Feather/Stata loaders honour this for fast partial reads.
data_sample_nNoOptional uniform random subsample size (seed=0, deterministic) — useful on huge panels.

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault

No arguments

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A4.6/5.0
Behavior5/5

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

Beyond the readOnlyHint annotation, the description discloses statistical assumptions, data preconditions, failure modes, and concrete corrective actions (trim to common support, re-specify with CBPS/entropy balancing). It also reveals that the tool is an alias for match, which is directly useful behavioral information.

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 and front-loaded, with each labeled section earning its place. It loses a point for the vague 'Validation: certified parity evidence' line and the internal ':func:`match`' syntax, which are not directly actionable for an agent selecting or invoking the tool.

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 selection context, validity assumptions, data prerequisites, failure modes, and alternatives; an output schema exists, so repeating return-value details is unnecessary. For a matching estimator with a rich generic parameter schema, this is a complete and decision-ready description.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

With 100% schema coverage, the baseline is 3, but the description adds real meaning to parameters: it clarifies that d is a binary or low-cardinality treatment indicator and X represents pre-treatment covariates. The schema's d description is otherwise a tautology, so this textual addition is valuable.

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 opening line, 'Propensity-score matching -- article alias for :func:`match`', identifies the operation, resource, and relationship to the canonical function in one phrase. It also names alternatives, which helps an agent distinguish psm from siblings such as propensity_score, cbps, ebalance, and dml.

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 gives clear context through Assumptions, Pre-conditions, and a dedicated Alternatives list, and it even suggests typical minimum N=200. It does not provide explicit if-then routing like 'use X when Y, otherwise use Z', but the preconditions and alternatives strongly signal when psm is appropriate.

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

Deploy Server

Other Tools