Skip to main content
Glama
vikranthviki

Causal Decision Agent

by vikranthviki
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Python
Local

msm

Read-only

Estimate causal effects of time-varying treatments while controlling time-varying confounders via stabilized inverse probability weighting, with cluster-robust inference.

Instructions

Marginal Structural Models for time-varying treatments with time-varying confounders. Uses stabilized IPTW and cluster-robust inference. Handles binary or continuous treatment; exposure summary can be current, cumulative, or ever. Validation: validated evidence tier (known-truth, reference, external-parity, or Monte Carlo artifact). Assumptions: Sequential exchangeability / no unmeasured confounding at each time point; Positivity: every treatment level is possible given the past; Correct specification of the treatment and/or outcome models. Pre-conditions: Sequentially measured covariates, (time-varying) treatment, and outcome; Models for the treatment process and the outcome (or weights). Failure modes: Stabilized weights have extreme values (positivity near-violation) -> Truncate weights, simplify the treatment model, or use a doubly-robust estimator (TMLE). Alternatives: sp.tmle, sp.g_computation, sp.ipw. Typical minimum N: 300.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
yYesOutcome
idYesUnit identifier
timeYesPeriod identifier
trimNoWeight truncation quantile
treatYesTime-varying treatment
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
familyNoOutcome familygaussian
baselineNoBaseline covariates
exposureNoExposure summarycumulative
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.
time_varyingYesTime-varying confounders (pre-treatment)
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

A4.4/5.0
Behavior5/5

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

The description discloses method behavior (stabilized IPTW, cluster-robust inference), supported treatment types, exposure summary options, and failure modes with actionable fixes. It also notes validation tier and typical minimum N. This goes well beyond the readOnlyHint annotation by explaining what the estimator does and when it may break.

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 moderately long but structured with clear labels (Assumptions, Pre-conditions, Failure modes, Alternatives). Each section adds value, though the 'Validation' sentence is somewhat peripheral.

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 complex causal inference tool, the description covers the core method, assumptions, data requirements, failure modes, alternatives, and sample size guidance. With an output schema present, the description is sufficiently complete for an agent to invoke it correctly.

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 15 parameters. The description adds minimal parameter context (e.g., exposure summary options, trim in failure mode) but does not systematically explain parameter relationships beyond the schema.

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 identifies the tool as fitting Marginal Structural Models for time-varying treatments with time-varying confounders, and details the estimation approach (stabilized IPTW, cluster-robust inference) and supported treatment/exposure types. This distinguishes it from sibling estimators like g_computation or ipw, and it explicitly names alternatives.

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 lists assumptions (sequential exchangeability, positivity, correct specification) and pre-conditions (sequential covariates, treatment, outcome, models) that indicate when the tool is appropriate. It also names alternatives (sp.tmle, sp.g_computation, sp.ipw) and provides a failure-mode recommendation. It does not explicitly state when not to use it, but the context is clear.

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