Causal Decision Agent

Overview Schema Source Related Servers Discussions Admin

etregress

Read-only

Corrects for endogenous treatment selection using instrumental variables, returning causal estimates and diagnostics for audit-ready business decisions.

Instructions

Endogenous treatment effects model. Validation: certified parity evidence.

Input Schema

TableJSON Schema

Name	Required	Description	Default
`x`	Yes	Exogenous regressors.
`y`	Yes	Outcome variable.
`z`	Yes	Instruments for the selection equation.
`tol`	No	Numerical convergence tolerance.
`alpha`	No	Significance level for confidence intervals and tests.
`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
`method`	No	``'mle'`` for full-information maximum likelihood (Stata's default) or ``'twostep'`` for the control-function estimator (Stata's ``twostep`` option). They are different estimators, not two routes to the same numbers.	mle
`robust`	No	``'nonrobust'`` (observed information), ``'robust'`` (sandwich, with Stata's ``N/(N-1)`` factor) or ``'cluster'``. Passing ``cluster=`` implies ``'cluster'``. ``vce=`` is accepted as an alias.	nonrobust
`cluster`	No	Cluster column. Uses Stata's ML cluster factor ``g/(g-1)``.
`maxiter`	No	maxiter parameter (int).
`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`	Yes	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://.
`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.
`treatment`	Yes	Binary treatment variable (0/1, both values present).
`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

C2.7/5.0

Behavior2/5

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

The annotations already declare readOnlyHint=true, so the tool's non-mutating nature is known. But the description adds no behavioral detail about what happens during execution, what the returned fit contains, or how the 'certified parity evidence' validation affects results. The second sentence is cryptic and does not clarify runtime behavior.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness2/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is short, but the second sentence 'Validation: certified parity evidence' is a confusing non-sequitur that does not earn its place. It distracts from the otherwise simple model label and makes the description feel unpolished.

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?

This is a complex econometric tool with 16 parameters and a rich output schema, yet the description provides only a terse model name. It lacks guidance on use cases, interpretation, relationship to competing estimators, and any orientation to the detailed parameters or return payload.

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 coverage is 100%, so the parameters are already well-described in the input schema. The description itself adds no parameter-level meaning, but since the schema carries the full burden, a baseline of 3 is appropriate.

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 'Endogenous treatment effects model,' which clearly identifies the statistical domain and distinguishes the tool from generic regress/ivreg/heckman alternatives. However, it lacks an explicit action verb like 'Estimates' or 'Fits,' so the purpose is conveyed by implication rather than direct statement.

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 provided on when to use this tool versus alternatives, what data prerequisites apply (e.g., binary endogenous treatment, instruments), or what situations call for a different estimator. The description gives no exclusions or context to help the agent choose this tool.

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

Deploy Server