StatsPAI

audit

Read-only

Run a reviewer-grade audit on a causal result: get the literature checklist with per-item status and the exact suggest_function to call for any missing high-importance check.

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.

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "audit"
  }
}

Input Schema

Name	Required	Description	Default
`detail`	No	Payload depth; agent is the fullest.	agent
`data_id`	No	Data handle (d_...) from load_data; replaces data_path.
`data_csv`	No	Small inline table as CSV text.
`as_handle`	No	Cache the fit and return its result_id.
`data_path`	No	Absolute path of a data file on the server.
`result_id`	No	Result handle. Required unless you also pass a fitted result via the result kwarg (programmatic use).
`data_records`	No	Small inline table as row objects.
`max_output_bytes`	No	Result byte budget (default 262144; 0 = none).

Output Schema

Name	Required	Description	Default
No arguments

Schema Changelog

Changes observed during successful MCP inspections.

First observedv0.1.0Nov 12, 2026

TDQS

A3.6/5.0

Behavior4/5

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

Annotations already declare readOnlyHint=true and openWorldHint=false, so the safety profile is covered. The description adds real behavioral value beyond that: the output is a checklist of named econometric checks with statuses, and missing high-importance items come with a concrete suggest_function to call. It does not mention cost or depth trade-offs, but the key behavioral shape is disclosed.

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?

Two tight sentences with the core action front-loaded and the return contents enumerated compactly. The parenthetical checklist is slightly listy but each item is informative rather than filler.

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?

For a read-only diagnostic with a full output schema, the description covers what it produces and what to do next. The notable gap is disambiguation from the sibling 'audit_result' in a crowded catalog, plus no indication of how the audit interacts with the several ways of supplying data or a fitted result.

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 every parameter including result_id, detail, and the data-passing alternatives is already documented in the schema. The description adds no parameter-level meaning, which is acceptable at full coverage but earns only the baseline.

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?

States a specific verb and resource: it runs a 'reviewer-grade audit on a result' and returns a literature checklist with per-item status plus suggested follow-up calls. That is materially more specific than the name alone. It does not, however, distinguish itself from the sibling 'audit_result', whose name suggests a very similar operation.

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?

Usage is only implied: the mention of filling 'missing high-importance checks' suggests this is a diagnostic step run after a result exists and before remediation. There is no explicit when-to-use vs. the near-identical 'audit_result' sibling, and no statement of prerequisites or when the audit is unnecessary.

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