Causal Decision Agent

Overview Schema Source Related Servers Discussions Admin

panel_unitroot

Read-only

Run panel unit root tests to determine whether a variable is stationary across units, using LLC, IPS, Fisher ADF, or Hadri methods with lag selection and trend options for reliable causal analysis.

Instructions

Panel unit root test. Validation: validated evidence tier (known-truth, reference, external-parity, or Monte Carlo artifact).

Input Schema

TableJSON Schema

Name	Required	Description	Default
`id`	No	Unit identifier.	id
`lags`	No	Number of ADF lags. If None, uses AIC selection.
`test`	No	Test type: 'llc' (Levin-Lin-Chu), 'ips' (Im-Pesaran-Shin), 'fisher' (Fisher-type ADF), 'hadri' (stationarity test).	ips
`time`	No	Time identifier.	time
`trend`	No	'n' (none), 'c' (constant), 'ct' (constant + trend).	c
`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
`variable`	Yes	Variable to test.
`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

C2.4/5.0

Behavior3/5

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

Annotations already declare readOnlyHint=true, so the safe read-only behavior is covered. The description adds a cryptic 'validated evidence tier' claim, which is a slight bonus beyond annotations, but it does not explain what that means or any other behavioral traits such as output shape or special limitations.

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 text is short but under-specified: the first sentence merely restates the tool name, and the second sentence is vague and unexplained. This is not efficient conciseness but rather missing content.

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 12-parameter tool with a rich schema, the description provides almost no contextual help for selecting among tests, interpreting validation tiers, or understanding when this tool is the right choice. The output schema exists, but the description still leaves the agent without enough orientation.

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 carries the parameter documentation burden. The description adds no additional meaning for parameters like lags, test, trend, detail, or data_path.

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 is a noun-phrase restatement of the tool name ('Panel unit root test') rather than a verb-driven statement of what the tool does. It does not distinguish this tool from related siblings such as 'ips', 'johansen', or other time-series/panel testing tools.

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 panel_unitroot versus alternatives, and no mention of exclusions or preferred contexts. The validation-tier sentence is about output evidence, not usage selection.

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

Deploy Server