Causal Decision Agent

Overview Schema Source Related Servers Discussions Admin

panel_fgls

Read-only

Estimate panel regression models using FGLS, correcting for heteroskedasticity and autocorrelation to produce evidence for rollout, hold, or investigate verdicts.

Instructions

Panel FGLS (Feasible Generalized Least Squares). Validation: certified parity evidence.

Input Schema

TableJSON Schema

Name	Required	Description	Default
`x`	Yes	Regressors.
`y`	Yes	Dependent variable.
`id`	No	Panel identifier.	id
`tol`	No	Numerical convergence tolerance.
`corr`	No	Within-panel correlation: 'independent', 'ar1' (panel-specific AR(1)), 'psar1' (common AR(1)).	independent
`igls`	No	Iterate the variance estimates to convergence (Stata's ``igls``). The default is the two-step estimator Stata's ``xtgls`` reports without that option. .. versionchanged:: 1.27.0 This function iterated unconditionally, so its default was Stata's ``igls`` while the docstring claimed equivalence to the plain command. On a balanced N=60, T=12 panel under ``panels(hetero)`` the two differ by 2.8% on the slope. Pass ``igls=True`` for the previous behaviour.
`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
`panels`	No	Error structure across panels: 'homoskedastic', 'heteroskedastic', 'correlated' (cross-sectional).	heteroskedastic
`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.
`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

C2.2/5.0

Behavior2/5

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

Annotations indicate readOnlyHint=truecars, so the safety profile is covered. However, the description adds no behavioral context such as what outputs are returned, whether the data is modified, or any side effects. The phrase 'certified parity evidence' hints at validation but does not describe the tool's runtime behavior in a useful way.

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 very brief, but the first sentence is redundant with the tool name and the second sentence is vague and uninformative. For a tool with 16 parameters, this is under-specification rather than effective conciseness; the sentences do not earn their place by adding value.

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?

Although the schema and output schema are rich, the description itself does not explain what the tool does, what inputs are expected beyond schema names, or how it relates to sibling tools. An agent cannot determine from the description alone when to invoke panel_fgls or what the tool accomplishes, making it contextually incomplete for a complex econometrics tool.

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 each parameter already has a description. The tool description adds no additional meaning or clarification about parameters. 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.

Purpose2/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description 'Panel FGLS (Feasible Generalized Least Squares)' essentially restates the tool name with the acronym expanded. It lacks an action verb (e.g., 'estimates', 'fits') that would clarify what the tool does. Mention of 'Validation: certified parity evidence' is tangential and does not explain the tool's core purpose.

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 about when to use this tool versus alternatives like xtgls, sureg, or other panel estimators. The description does not mention any conditions, prerequisites, or scenarios where panel_fgls is preferred, leaving the agent to infer usage from the name alone.

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

Deploy Server