Causal Decision Agent

Overview Schema Source Related Servers Discussions Admin

fortified_pci

Read-only

Estimates ATT via fortified proximal causal inference, adding a bridge-function stability constraint for robust results under mild misspecification. Requires valid negative-control proxies.

Instructions

Fortified proximal causal inference (Yu, Shi & Tchetgen Tchetgen 2025). Adds a bridge-function stability constraint that gives robust ATT under mild misspecification of the outcome/treatment bridge. Validation: validated evidence tier (known-truth, reference, external-parity, or Monte Carlo artifact). Assumptions: The proxies are valid negative controls (relevant to the confounder, excluded from the causal channel); A bridge function exists (completeness conditions hold). Pre-conditions: Treatment-inducing and outcome-inducing proxy variables (negative controls) for the unobserved confounder. Failure modes: Proxies are weak or invalid -- the bridge function is poorly identified -> Test proxy relevance, select stronger proxies, or fall back to sensitivity analysis. Alternatives: sp.select_pci_proxies, sp.dml. Typical minimum N: 500.

Input Schema

TableJSON Schema

Name	Required	Description	Default
`y`	Yes	Outcome variable column name or outcome array.
`treat`	Yes	Treatment indicator or first-treatment-period column.
`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
`proxy_w`	Yes	Outcome-side proxies
`proxy_z`	Yes	Treatment-side proxies
`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.
`covariates`	No	Covariate matrix, DataFrame, or column names.
`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

A4.6/5.0

Behavior4/5

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

Annotations already declare readOnlyHint=true, so the description does not need to repeat safety behavior. It adds contextual details about assumptions and failure modes that go beyond annotations, though it does not elaborate on side effects or return semantics (covered by output schema). This is adequate given the annotation coverage.

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?

The description is well-structured with labeled sections (Validation, Assumptions, Pre-conditions, Failure modes, Alternatives, Typical N) and is front-loaded with the method name and core purpose. It is longer than a typical description but each sentence serves a distinct purpose, and the structure improves scannability.

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 causal inference method, the description covers the method, assumptions, pre-conditions, failure modes, alternatives, and typical sample size. An output schema exists, so return details are not required. This is complete for an agent to determine when and how to use the tool.

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?

Schema description coverage is 100%, so each parameter is already documented. The description adds meaning by explaining the role of proxies as negative controls in the pre-conditions, which clarifies the purpose of proxy_w and proxy_z beyond the schema's brief descriptions. It does not fully compensate for the schema's brevity on these parameters but adds value.

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 clearly identifies the method (fortified proximal causal inference), states it estimates ATT with a bridge-function stability constraint, and explicitly names alternatives (sp.select_pci_proxies, sp.dml), distinguishing it from sibling tools. The purpose is specific and actionable.

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

Usage Guidelines5/5

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

It provides explicit pre-conditions (treatment-inducing and outcome-inducing proxy variables as negative controls), failure modes with recommended actions (test proxy relevance, select stronger proxies, or fall back to sensitivity analysis), and names alternatives. This gives an agent clear when-to-use and when-not-to-use guidance.

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

Deploy Server