Causal Decision Agent

by vikranthviki

Overview Schema Source Related Servers Discussions Admin

Python

Local

rlasso_iv

Read-only

Estimate causal effects with instrumental variables using rigorous Lasso to select valid instruments and controls.

Instructions

Instrumental-variables estimation with rigorous-Lasso selection.

Input Schema

TableJSON Schema

Name	Required	Description	Default
`d`	Yes	name).
`x`	No	Primary running variable, regressor, or feature input for this estimator.
`y`	Yes	name).
`z`	Yes	Instrument, proxy, or auxiliary variable used by this estimator.
`post`	No	Post-Lasso (OLS refit) inside every selection step.
`detail`	No	Payload 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
`control`	No	Forwarded to :func:`statspai.rlasso.rlasso` (penalty level, loadings, iteration controls).
`penalty`	No	Forwarded to :func:`statspai.rlasso.rlasso` (penalty level, loadings, iteration controls).
`select_X`	No	Lasso-select among the controls (partialling-out).
`select_Z`	No	Lasso-select among the instruments.
`as_handle`	No	If 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_path`	No	Absolute 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://.
`intercept`	No	Passed to the underlying ``rlasso`` first stages.
`result_id`	No	Optional 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_columns`	No	Optional column projection. Parquet/Feather/Stata loaders honour this for fast partial reads.
`data_sample_n`	No	Optional uniform random subsample size (seed=0, deterministic) — useful on huge panels.

Output Schema

TableJSON Schema

Name	Required	Description	Default
No arguments

Schema Changelog

Changes observed during successful MCP inspections.

First observedv0.1.0Sep 15, 2026

TDQS

B3.4/5.0

Behavior3/5

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

Annotations declare readOnlyHint=true, and the description does not contradict this. The description adds the 'rigorous-Lasso selection' behavior, which is useful, but it does not disclose details such as whether the function returns a fitted object, whether it performs partialling-out, or how selection is structured. With annotations covering the safety profile, a 3 is appropriate.

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 concise sentence that front-loads the core method and its distinguishing feature. It is efficient and not padded, though it could have added a bit more context without becoming verbose.

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?

Given the tool's complexity (16 params, nested objects, output schema present), the description is minimal but the schema and output schema fill many gaps. However, the description does not explain the intended workflow (e.g., data_path + column names, as_handle chaining) or how this tool relates to rlasso_effect/rlasso_effects siblings. It is adequate but not complete.

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 16 parameters. The description adds no parameter-level meaning beyond the schema, but the schema descriptions are fairly informative (e.g., 'Post-Lasso (OLS refit) inside every selection step'). Baseline 3 is correct when the schema carries the burden.

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 'Instrumental-variables estimation with rigorous-Lasso selection' clearly identifies the method (IV estimation) and the distinguishing feature (rigorous-Lasso selection). It is specific enough to differentiate from plain 'iv' or 'ivreg' siblings, though it does not explicitly name a sibling or elaborate on the estimator's role.

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

Usage Guidelines3/5

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

The description implies usage for IV settings with many instruments/controls where Lasso selection is needed, but it does not explicitly state when to prefer this over alternatives like ivreg, lasso_iv, or rlasso_effect. No exclusions or alternative tool names are given, so the agent must infer the context from the method name.

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

Deploy Server