Skip to main content
Glama
vikranthviki

Causal Decision Agent

by vikranthviki

rlasso_effect

Read-only

Estimates the causal effect of a treatment on an outcome after Lasso automatically selects relevant controls from a provided set.

Instructions

Effect of d on y after Lasso-selecting controls x.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
dYesd parameter (Union[np.ndarray, pd.Series, str]).
xYesPrimary running variable, regressor, or feature input for this estimator.
yYesOutcome variable column name or outcome array.
I3NoAmelioration set forced into the control set (double-selection only) -- hdm's ``I3`` argument.
postNoPost-Lasso inside the selection steps.
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
methodNoSee the module docstring.partialling out
controlNoForwarded to :func:`statspai.rlasso.rlasso`.
penaltyNoForwarded to :func:`statspai.rlasso.rlasso`.
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_pathNoAbsolute 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

B3.3/5.0
Behavior3/5

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

The annotations already declare readOnlyHint=true, so the agent knows this is a safe operation. The description adds one meaningful behavioral detail: Lasso-based control selection happens before estimating the effect. It does not disclose estimator assumptions, required preprocessing, or edge-case behavior, but with annotations covering the safety profile, this is acceptable.

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 a single front-loaded sentence with no filler, efficiently communicating the core purpose. It is appropriately terse, though it omits potentially useful context such as estimator family or relationship to sibling tools.

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?

With 14 parameters but only 3 required, detailed schema descriptions, an output schema, and read-only annotations, much of the invocation detail is covered elsewhere. However, the description leaves ambiguity about whether this tool handles a single treatment effect versus multiple effects (as in `rlasso_effects`) and what model family is assumed, so it is not fully complete for an agent selecting among near-identical siblings.

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?

Schema description coverage is 100%, which establishes a baseline of 3. The description adds role semantics by mapping `d` to the treatment, `y` to the outcome, and `x` to the controls selected by Lasso, which is more informative than the schema's generic phrasing such as 'd parameter' and 'Primary running variable, regressor, or feature input.'

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 description states a specific purpose: estimating the effect of `d` on `y` while using Lasso to select controls from `x`. This is clear and non-tautological. It does not explicitly distinguish itself from near-identical siblings like `rlasso_effects` or `rlassologit_effect`, so it falls short of a 5.

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

Usage Guidelines2/5

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

No guidance is given about when to prefer this tool over alternatives such as `rlasso_effects`, `rlassologit_effect`, `rlasso_iv`, or `lasso_select`. The phrase 'after Lasso-selecting controls' weakly implies a high-dimensional-control setting, but there is no explicit when/when-not routing or mention of alternative tools.

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