Causal Decision Agent

Overview Schema Source Related Servers Discussions Admin

recommend

Read-only

Identify the right causal estimator for your dataset and research question: returns a ranked list with reasoning, precondition checks, and a complete workflow.

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.

Input Schema

TableJSON 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: '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
`verify`	No	If True, run resampling-stability checks on top recommendations.
`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.
`treatment`	No	Treatment / exposure column.
`covariates`	No	Covariate columns.
`instrument`	No	Instrumental variable.
`running_var`	No	Running variable (RD).
`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

A4.5/5.0

Behavior4/5

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

Annotations already declare readOnlyHint = true, so the agent knows this is risk-free. The description adds meaningful behavioral detail beyond that: the tool returns reasoning, precondition checks, and a full suggested workflow, and can optionally run resampling-stability verification. This gives the caller a realistic picture of what invoking the tool will produce.

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?

Three sentences with no filler. The first sentence states the core purpose, the second gives actionable placement in the agent's workflow, and the third enumerates important supported capabilities. Every sentence earns its place.

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

Completeness5/5

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

For a complex 16-parameter tool with an output schema and read-only annotations, the description is complete enough. It explains the role of the tool, its output shape, supported analysis scenarios, and how it fits into a multi-call workflow. The rich input schema and output schema cover the remaining details.

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

Parameters4/5

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

The input schema already documents all 16 parameters with 100% coverage, so the baseline is 3. The description adds value beyond the schema by highlighting DAG input and mediator/proxy/principal-strata support, which are not obvious from individual parameter names, and by noting the optional resampling-stability verification that maps to the 'verify' parameter.

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?

The description states a specific verb ('recommends'), a specific resource ('a ranked list of estimators'), and the core job: given dataset + research question. It also differentiates from siblings by positioning itself as the first call an agent should make when uncertain which estimator to run.

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?

The description explicitly says when to use this tool: 'This is the first call an agent should make if it doesn't know which estimator to run.' It also sketches supported scenarios (DAG input, mediator/proxy/principal-strata variables, optional verification). It stops short of naming specific alternatives or exclusion conditions, but the guidance is clear enough for routing.

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

Deploy Server