Skip to main content
Glama
vikranthviki

Causal Decision Agent

by vikranthviki

rlasso

Read-only

Select relevant covariates and estimate causal effects using rigorous Lasso or post-Lasso, with diagnostics for violations and next steps.

Instructions

Rigorous Lasso / post-Lasso -- a faithful port of hdm::rlasso.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
XYesDesign matrix of candidate covariates (``p`` may exceed ``n``).
yYesResponse.
rngNoOnly used when ``X.dependent.lambda`` simulation is requested.
postNoIf ``True``, re-estimate the selected support by OLS (post-Lasso).
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
controlNoOverrides for ``numIter`` (default 15), ``tol`` (default 1e-5) and ``threshold`` (default ``None``).
penaltyNoOverrides for ``homoscedastic`` (``True`` / ``False`` / ``"none"``), ``X.dependent.lambda`` (bool), ``c`` (slack, default 1.1), ``gamma`` (default ``0.1/log(n)``), ``lambda.start`` and ``numSim``. Defaults reproduce hdm exactly.
colnamesNoNames for the columns of ``X`` (default ``V1..Vp``).
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://.
interceptNoCenter ``X`` and ``y`` and report an intercept on the original scale.
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

C2.9/5.0
Behavior3/5

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

The annotations already declare readOnlyHint=true and openWorldHint=false, covering the safety profile. The description adds one useful behavioral cue: it is a 'faithful port' of hdm::rlasso, implying default behavior and estimation semantics match that R package. However, it does not describe other behavioral aspects such as convergence behavior, runtime, or what exactly the returned object contains.

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 is a single, compact sentence with no filler, which is good for conciseness. But it is also sparse for a 14-parameter tool with a large sibling family; it front-loads the port identity yet omits any orientation about what the model does or when to use it. It is not over-written, but it is under-specified.

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

Completeness2/5

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

Given the tool's complexity (14 parameters, nested objects, many closely related siblings) the one-line description is not enough. The schema and output schema carry parameter and return-value details, but the description fails to provide context on how this tool fits into the wider lasso workflow or why an agent should invoke it over rlasso_iv, rlassologit, or rlasso_effect.

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 carries full parameter documentation. The description itself adds no parameter-level meaning; it only names the method. Per the rubric, a baseline of 3 is appropriate when the schema does the heavy lifting.

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 names a specific method and resource: 'Rigorous Lasso / post-Lasso' and ties it to the R package hdm::rlasso. It is not a tautology and clear to a statistically literate agent, but it never states an explicit verb like 'fit' and does not explicitly distinguish itself from sibling tools such as rlasso_iv or rlassologit.

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?

There is no guidance on when to choose rlasso over alternatives. Siblings include closely related estimators (rlasso_iv, rlassologit, rlasso_effect), and the description does not mention when the linear/post-Lasso variant is appropriate or when another tool should be used. Nothing tells the agent about prerequisites, data structure expectations, or fallbacks.

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