Skip to main content
Glama
vikranthviki

Causal Decision Agent

by vikranthviki
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Python
Local

lasso_iv

Read-only

Selects causal instruments via LASSO and runs IV estimation, providing tests for weak instruments, overidentification, and endogeneity to guide reliable decisions.

Instructions

LASSO-selected instrumental variables. Validation: validated evidence tier (known-truth, reference, external-parity, or Monte Carlo artifact). Assumptions: Relevance: instruments predict the endogenous regressor (first-stage F >= 10 rule of thumb); Exclusion: instruments affect outcome only through the endogenous regressor; Monotonicity (for LATE interpretation under heterogeneous effects). Pre-conditions: formula includes the (endog ~ instruments) parenthesised block; at least as many instruments as endogenous regressors (order condition); instruments are not themselves endogenous in the outcome equation. Failure modes: First-stage F < 10 (Stock-Yogo 5% bias) -> Use weak-IV-robust inference (Anderson-Rubin) or LIML; Over-identification test rejects (sp.estat 'overid') -> At least one instrument is invalid; drop instruments or switch to just-identified LIML; Hausman endogeneity test fails to reject -> OLS may be consistent and more efficient; report both. Alternatives: sp.deepiv, sp.bartik, sp.proximal, sp.regress. Typical minimum N: 100.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
dNod parameter (Optional[Any]).
yYesOutcome variable column name or outcome array.
zNoFull set of candidate instruments.
alphaNoSignificance level for confidence intervals and tests.
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
robustNoRobust standard-error or covariance estimator option.robust
x_exogNox_exog parameter (Optional[List[str]]).
clusterNoCluster identifier column for clustered standard errors.
penaltyNoInstrument selection criterion: 'bic', 'aic', 'cv'.bic
x_endogNox_endog parameter (Optional[List[str]]).
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

A3.9/5.0
Behavior4/5

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

Annotations only provide readOnlyHint=true and openWorldHint=false; the description adds substantial behavior-relevant context: first-stage F thresholds, overidentification and Hausman failure modes, and a typical minimum N. It does not contradict the read-only annotation because it describes diagnostics, assumptions, and validation rather than writes.

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 dense but well-labeled (Validation, Assumptions, Pre-conditions, Failure modes, Alternatives, Typical minimum N), and the core purpose is front-loaded. Some Stata-specific references ('sp.estat', the formula block) add minor noise, but there is no filler.

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

Completeness4/5

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

For a complex IV tool with 15 parameters, the description covers assumptions, failure modes, alternatives, validation tier, and sample-size guidance, while an output schema exists to document return values. The only real gap is the slight mismatch between the formula-based precondition and the column-based input schema.

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% for all 15 parameters, so the description does not need to repeat parameter documentation. The only parameter-adjacent content is the parenthesised formula precondition and the LASSO selection idea, which map only loosely to schema fields such as z and penalty.

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

Purpose4/5

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

The opening phrase 'LASSO-selected instrumental variables' identifies the resource and method, and the LASSO-selection emphasis distinguishes it from generic iv/ivreg siblings. However, it lacks an explicit verb such as 'estimates' or 'selects,' so the precise operation is inferred rather than stated.

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 pre-conditions (order condition, formula block, exogeneity of instruments), failure-mode guidance (first-stage F<10, overidentification, Hausman), and an Alternatives list (sp.deepiv, sp.bartik, sp.proximal, sp.regress). It stops short of an explicit when-to-use rule, such as 'use when there are many candidate instruments and LASSO selection is desired.'

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