Causal Decision Agent

Overview Schema Source Related Servers Discussions Admin

ivqreg

Read-only

Estimate causal quantile treatment effects with instrumental variables, handling endogeneity via Chernozhukov-Hansen quantile regression.

Instructions

Instrumental-variable quantile regression (Chernozhukov-Hansen). Validation: validated evidence tier (known-truth, reference, external-parity, or Monte Carlo artifact).

Input Schema

TableJSON Schema

Name	Required	Description	Default
`y`	Yes	Outcome variable.
`tau`	No	Quantile(s) of interest in ``(0, 1)``.
`exog`	No	Exogenous controls ``X`` (may be empty).
`alpha`	No	Significance level for confidence intervals.
`endog`	Yes	Endogenous regressor(s) ``D``.
`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
`n_grid`	No	Grid resolution for the profile search over ``alpha`` (scalar case) -- ignored when ``endog`` is multi-dimensional.
`refine`	No	After the grid search, refine ``alpha`` with a local optimizer.
`verbose`	No	verbose parameter (bool).
`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.
`bootstrap`	No	Number of pairs-bootstrap replications for standard errors. ``0`` disables bootstrap; asymptotic rank-test inversion is not implemented in this MVP.
`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.
`instruments`	Yes	Instrument(s) ``Z``. Must be at least as many as ``endog``.
`add_constant`	No	add_constant parameter (bool).
`data_columns`	No	Optional column projection. Parquet/Feather/Stata loaders honour this for fast partial reads.
`random_state`	No	Random seed or RandomState for reproducible stochastic steps.
`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

C2.9/5.0

Behavior3/5

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

Annotations already carry `readOnlyHint: true`, so the description does not need to restate safety. It adds no behavioral context beyond the method name, and the 'Validation' sentence is about evidence tier rather than tool behavior, which is mildly irrelevant.

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 short and front-loaded with the method, but the second sentence about 'Validation: validated evidence tier...' does not help an agent select or invoke the tool. It is compact yet contains an unhelpful clause.

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?

With 18 parameters, 4 required, and a specialized estimator, the description is too sparse to orient the agent on required inputs or when this is the right tool. Output schema and 100% parameter coverage mitigate some gaps, but no usage context is provided.

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 parameters like `endog`, `instruments`, `tau`, and `alpha` are already documented. The description adds no parameter-level guidance, but the baseline of 3 is appropriate because the schema carries the full 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 names the exact estimator ('Instrumental-variable quantile regression') and cites the method (Chernozhukov-Hansen), so an agent can distinguish it from plain `ivreg` or `qreg`. It lacks an explicit verb like 'estimates' and doesn't spell out the model, but the meaning is unambiguous.

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 this tool over the many sibling estimators (`ivreg`, `qreg`, `qte`, `sqreg`). The method name implies endogeneity + quantile effects, but the description never states conditions, exclusions, or alternatives.

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

Deploy Server