Causal Decision Agent

Overview Schema Source Related Servers Discussions Admin

estat

Read-only

Run post-estimation diagnostic tests on fitted models to identify violations, assess model validity, and determine next actions.

Instructions

Unified post-estimation diagnostics dispatcher.

Input Schema

TableJSON Schema

Name	Required	Description	Default
`lags`	No	Number of lags for the Breusch-Godfrey test.
`test`	No	Name of the diagnostic test. One of ``'hettest'``, ``'white'``, ``'reset'``, ``'ovtest'``, ``'bgodfrey'``, ``'dwatson'``, ``'vif'``, ``'ic'``, ``'linktest'``, ``'normality'``, ``'leverage'``, ``'endogenous'``, ``'overid'``, ``'firststage'``, ``'all'``.	all
`alpha`	No	Significance level for interpretation strings.
`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
`powers`	No	Highest power of y-hat for the RESET test.
`result`	Yes	A fitted result object with ``params``, ``data_info``, etc.
`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`	No	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.
`print_results`	No	If True, print a formatted table to stdout.

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

C2.6/5.0

Behavior2/5

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

Annotations already declare readOnlyHint=true and openWorldHint=false, so the safe-read behavior is covered by structured data. The description adds no behavioral specifics beyond the label 'dispatcher'; it does not disclose chaining/caching behavior, result format, or side-effect profile, though annotations cover the main safety trait.

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 a single, front-loaded noun phrase with no wasted words. It is concise, though arguably under-specified; still it earns a high conciseness score for efficiency.

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?

Despite a complete schema and output schema, the tool is complex (12 parameters, 15 possible tests) and the description provides almost no contextual guidance, such as when to use this dispatcher vs. sibling diagnostics or how tests are selected. This is insufficient for a tool of this complexity.

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 coverage is 100%, so all 12 parameters are individually described in the input schema. The description itself contributes no parameter semantics, but the baseline of 3 applies because the schema carries the full documentation burden.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose3/5

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

Description identifies the tool as a unified dispatcher for post-estimation diagnostics, which is a clear functional category, but it is vague: it names no specific diagnostic tests and does not distinguish this tool from sibling-specific test tools like reset_test or vif. It is more than a tautology but lacks a specific verb/resource.

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 usage guidance is provided. The description does not state when to invoke this dispatcher versus individual sibling diagnostic tools, nor any prerequisites or conditions. An agent must rely on the schema and sibling names to infer applicability.

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

Deploy Server