Causal Decision Agent

Overview Schema Source Related Servers Discussions Admin

interactive_fe

Read-only

Estimate interactive fixed effects models on panel data to control for unobserved common factors and unit-specific heterogeneity.

Instructions

Interactive fixed effects estimator (Bai 2009). Validation: validated evidence tier (known-truth, reference, external-parity, or Monte Carlo artifact).

Input Schema

TableJSON Schema

Name	Required	Description	Default
`x`	Yes	Regressors.
`y`	Yes	Dependent variable.
`id`	No	Unit identifier.	id
`tol`	No	Numerical convergence tolerance.
`time`	No	Time identifier.	time
`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	'iterative' (Bai 2009 CCE-type), 'pca' (principal components).	iterative
`robust`	No	Robust standard-error or covariance estimator option.
`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://.
`n_factors`	No	Number of interactive factors (r).
`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

C2.9/5.0

Behavior2/5

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

Annotations already mark the tool as read-only, and the description adds no behavioral context beyond that: no mention of data requirements, convergence behavior, side effects, caching, or how the fitted result is returned. The 'Validation: validated evidence tier' sentence describes a validation property, not tool behavior.

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 very short with no filler, and the estimator label is front-loaded. The second validation sentence is cryptic and contributes little to invocation, preventing a perfect score.

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?

For a complex 16-parameter estimator, the description leaves out essential context: required panel structure, when interactive fixed effects are appropriate, or how this differs from the many sibling estimators. The detailed schema and output schema compensate for return-value documentation, but not for missing usage and model-selection context.

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, giving a baseline of 3. The description does not add parameter-level context beyond naming the model family, which weakly informs n_factors and method but contributes no concrete parameter semantics.

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 clearly identifies the tool as an interactive fixed effects estimator and anchors it to Bai (2009), which is specific enough to convey the method. However, it is a noun phrase rather than an action statement, and it does not differentiate the tool from closely related siblings such as gsynth or fect.

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 use this estimator versus alternatives like feols, twoway FE, gsynth, or matrix_completion. The validation-tier sentence is unrelated to selection criteria, so the agent must infer applicability solely 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