Causal Decision Agent

Overview Schema Source Related Servers Discussions Admin

audit

Read-only

Reviews a fitted causal result against the literature checklist, showing which checks pass or fail and suggesting the next function to run for missing high-importance items.

Instructions

Reviewer-grade audit on a result. Returns the literature checklist (parallel-trends test, honest-DID, Bacon decomposition, placebo, balance, ...) with status per item and the concrete suggest_function to call to fill any missing high-importance check.

Input Schema

TableJSON Schema

Name	Required	Description	Default
`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`	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	Result handle. Required unless you also pass a fitted result via the result kwarg (programmatic use).
`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

A3.7/5.0

Behavior4/5

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

Annotations already declare readOnlyHint=true, and the description is consistent with that. The description adds value beyond annotations by specifying the behavioral output shape: a literature checklist with per-item status and a concrete suggested function for missing checks. This is useful context for an agent planning next steps.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Two tight sentences with no filler. The first sentence states the function and scope, and the second explains the output contract. Every sentence earns its place and the key idea is front-loaded.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness3/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With an output schema present and rich parameter descriptions, the description does not need to restate parameter or return details. It is adequate but minimal: it lacks workflow context such as 'call after fitting a result' and does not distinguish audit from semantically overlapping siblings, leaving selection among similar tools partially unresolved.

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 individual parameter descriptions (detail levels, as_handle caching, data_path formats, result_id, projection, sampling) already carry the semantic load. The description adds no parameter-level detail, but it does not need to compensate because the schema is thorough. Baseline 3 is appropriate.

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 states the tool performs a 'reviewer-grade audit on a result' and enumerates concrete checks (parallel-trends, honest-DID, Bacon decomposition, placebo, balance) plus the output form (status per item, suggested follow-up function). However, it does not explicitly differentiate itself from closely related siblings like audit_result, assumption_audit, diagnose, or robustness_report.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines3/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The phrase 'audit on a result' implies the tool is used after a fitted result exists, and the mention of 'suggest_function to fill any missing high-importance check' hints at a follow-up workflow. But there is no explicit when-to-use guidance, prerequisites, or exclusion of alternatives, and the large sibling list makes this omission more costly.

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

Deploy Server