Causal Decision Agent

Overview Schema Source Related Servers Discussions Admin

pci_mtp

Read-only

Estimates the effect of a modified treatment policy (e.g., raising a dose) under unobserved confounding, using proximal causal inference with negative-control proxy variables.

Instructions

Proximal causal inference for modified treatment policies (Park & Ying 2025). Estimates the effect of a policy that shifts the treatment distribution (e.g., raises the dose by 10%) under unobserved confounding identified by PCI. 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.
`delta`	Yes	Additive shift applied to the treatment under the modified policy
`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	proxy_w parameter (list).
`proxy_z`	Yes	proxy_z parameter (list).
`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

A4.7/5.0

Behavior5/5

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

Annotations provide readOnlyHint=true, so the description need not restate safety. It goes beyond that by disclosing assumptions (valid negative controls, bridge function), pre-conditions, and failure modes (weak/invalid proxies leading to poor identification). This gives an agent accurate expectations about execution outcomes, far exceeding 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.

Conciseness5/5

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

The description is a single focused paragraph with clear internal structure (Assumptions, Pre-conditions, Failure modes, Alternatives, Typical N). It front-loads the core purpose and packs essential context into each sentence without redundancy. Every element 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 estimator with assumptions and pre-conditions, this description fully equips an agent: it covers prerequisites, failure modes, alternatives, and typical sample size. Since an output schema exists (indicated by 'Has output schema: true'), the description doesn't need to explain return values, so nothing critical is missing.

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 11 parameters with individual descriptions. The tool description adds conceptual context (e.g., what 'delta' is for) but doesn't elaborate beyond the schema. With full coverage, the baseline of 3 is appropriate; the description adds minimal extra parameter-level meaning.

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 ('estimates') with a clear resource ('effect of a policy that shifts the treatment distribution') and identifies the method (PCI). It also names alternative tools explicitly (sp.select_pci_proxies, sp.dml), distinguishing it from siblings without needing to inspect schemas.

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?

The description gives explicit when-to-use context (unobserved confounding identified by PCI), states pre-conditions (treatment-inducing and outcome-inducing proxies), lists failure modes and fallback actions, and names alternatives. This is comprehensive routing guidance beyond what annotations provide.

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

Deploy Server