StatsPAI

recommend

Read-only

Suggests ranked causal estimators with reasoning, precondition checks, and a suggested workflow from a dataset and research question, so agents can choose the right method before fitting.

Instructions

Method advisor: given a dataset + research question, recommends a ranked list of estimators with reasoning, precondition checks, and a full suggested workflow. This is the first call an agent should make if it doesn't know which estimator to run. Supports DAG input, mediator / proxy / principal-strata variables, and optional resampling-stability verification.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "y": "<y>"
    },
    "name": "recommend"
  }
}

Input Schema

Name	Required	Description	Default
`y`	Yes	Outcome column.
`id`	No	Unit identifier (panel).
`time`	No	Time column (panel / DID).
`cutoff`	No	RD cutoff value.
`design`	No	Override auto-detected design.
`detail`	No	Payload depth; agent is the fullest.	agent
`verify`	No	If True, run resampling-stability checks on top recommendations.
`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	Handle of an earlier fit made with as_handle=true.
`treatment`	No	Treatment / exposure column.
`covariates`	No	Covariate columns.
`instrument`	No	Instrumental variable.
`running_var`	No	Running variable (RD).
`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

A3.7/5.0

Behavior3/5

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 useful behavioral detail about what comes back (ranked list, reasoning, precondition checks, workflow) and that verify adds resampling-stability checks. It omits that this is advice-only and does not fit/return an actual estimate, and gives no sense of cost or latency when verify=true, which matters for an 18-parameter call.

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?

Three sentences, front-loaded with purpose, then routing guidance, then capabilities — no filler. The final capabilities sentence is the weakest, since it spends words on features not present in the schema, but the structure itself is clean.

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?

An output schema exists so return values need not be spelled out, and the description correctly stays high-level about them. However, for a tool with 18 parameters spanning data handles, design overrides, and variable roles, the description names almost none of them, and its advertised DAG/mediator/proxy/principal-strata support has no schema backing — leaving a real gap between promise and interface.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters2/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

With 100% schema description coverage the baseline would be 3, but the description actively misleads: it claims support for "DAG input, mediator / proxy / principal-strata variables", yet the input schema contains no dag, mediator, proxy, or principal-strata parameter. Only the resampling-stability/verify link maps to a real parameter. This creates expectations the schema cannot satisfy, which is worse than adding nothing.

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

Purpose5/5

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

States a specific verb and deliverable — "recommends a ranked list of estimators with reasoning, precondition checks, and a full suggested workflow" — plus the inputs it consumes (dataset + research question). It also positions itself against the sibling family (detect_design, causal, the estimator-specific tools) by declaring itself the advisory entry point, so an agent can tell what it is without opening the schema.

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

Usage Guidelines4/5

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

"This is the first call an agent should make if it doesn't know which estimator to run" gives a concrete trigger condition and implicitly excludes agents that already know the estimator. It does not name a specific alternative for the known-estimator case (e.g., go straight to feols/dml/pipeline_*) nor state when not to call it, so it stops short of full routing guidance.

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