Causal Decision Agent

Overview Schema Source Related Servers Discussions Admin

engle_granger

Read-only

Apply a two-step cointegration test to time series data, identifying long-run equilibrium relationships to support evidence-based business decisions.

Instructions

Engle-Granger (1987) two-step cointegration test. Validation: validated evidence tier (known-truth, reference, external-parity, or Monte Carlo artifact).

Input Schema

TableJSON Schema

Name	Required	Description	Default
`lags`	No	Lags for ADF test. If None, uses AIC selection.
`alpha`	No	Significance level for confidence intervals and tests.
`trend`	No	trend parameter (str).	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
`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.
`variables`	No	Variables to test (first is dependent).
`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

C2.8/5.0

Behavior2/5

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

Annotations already mark it read-only, but the description adds no behavioral context beyond that tag, such as the ADF regression on residuals or assumptions about variable integration order. It does not contradict the annotations.

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 first sentence is an efficient front-loaded purpose statement. The second sentence about validation evidence is not actionable for a caller and does not earn its place, though the overall length is still short.

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 specialized econometric tool with 10 parameters and a large sibling set, the description leaves out prerequisites and selection context such as needing two or more I(1) variables or using johansen for multiple cointegrating relationships. The output schema covers return values, but the definition is thin for call-time decisions.

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%, and the description itself adds no parameter-level meaning. Baseline 3 is appropriate because the schema already documents lags, alpha, trend, detail, and data options in sufficient detail.

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 statistical method — Engle-Granger (1987) two-step cointegration test — so an agent knows the routine performs a specific estimation. It is concise and immediately clear, though it does not differentiate the test from sibling cointegration tools such as johansen.

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 when-to-use guidance, exclusions, or alternatives are given. The only additional sentence is a validation-evidence tag, which says nothing about when to call this tool instead of another test.

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

Deploy Server