Causal Decision Agent

Overview Schema Source Related Servers Discussions Admin

frontdoor

Read-only

Estimate the causal effect of a treatment on an outcome through a mediator by applying front-door adjustment, returning validated evidence tiers and actionable verdicts for business decisions.

Instructions

Front-door adjustment -- article-friendly alias for Validation: validated evidence tier (known-truth, reference, external-parity, or Monte Carlo artifact).

Input Schema

TableJSON Schema

Name	Required	Description	Default
`X`	No	Feature matrix or covariate DataFrame.
`d`	Yes	d parameter (str).
`m`	Yes	m parameter (str).
`y`	Yes	Outcome variable column name or outcome array.
`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`	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.
`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

C2.2/5.0

Behavior2/5

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

The readOnlyHint annotation already covers the safety profile, so the description's job is to add behavioral context beyond that. It does not describe side effects, output behavior, error cases, or operational constraints; the cryptic 'validated evidence tier' fragment adds little concrete behavioral information.

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

Conciseness2/5

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

The description is short, but brevity here is under-specification rather than effective conciseness. The sentence is front-loaded with the tool name and then trails into an opaque 'Validation' alias phrase that does not earn its place.

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 the output schema and fully described parameters, the description fails to orient the agent on the core purpose, invocation context, or relationship to sibling tools. For a 10-parameter causal inference tool, this is an inadequate orienting statement.

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 the schema already documents all parameters and the baseline is 3. The description adds no parameter-level meaning and does not clarify how d, m, and y relate to front-door adjustment.

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

Purpose2/5

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

The description names 'Front-door adjustment' but never states a concrete verb or outcome (e.g., estimate, compute, return). The phrase 'article-friendly alias for Validation: validated evidence tier' is confusing and does not explain what the tool actually does with the supplied d, m, y, and data_path. It also does nothing to distinguish this tool from the similarly named sibling front_door.

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 guidance is provided about when to use this tool versus alternatives such as front_door or other causal inference tools. The 'alias' phrasing hints at naming but gives no actionable selection criteria or exclusions.

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

Deploy Server