Causal Decision Agent

Overview Schema Source Related Servers Discussions Admin

negative_control_outcome

Read-only

Detect residual confounding using a negative-control outcome; a nonzero treatment coefficient signals unmeasured confounding, prompting additional covariate adjustment or sensitivity analysis.

Instructions

Lipsitch-style NCO calibration. Assumptions: The negative-control outcome is not caused by the treatment (Lipsitch-style calibration); It shares confounders with the real outcome. Pre-conditions: data has a negative-control outcome and a treatment column. Failure modes: Coefficient on treatment differs significantly from zero -- residual confounding detected -> Condition on more covariates or quantify the implied bias with a sensitivity analysis. Alternatives: sp.negative_control_exposure, sp.sensemakr, sp.evalue. Typical minimum N: 100.

Input Schema

TableJSON Schema

Name	Required	Description	Default
`nco`	Yes	Negative-control outcome -- a variable plausibly unaffected by the true treatment but sharing confounders with the real Y.
`alpha`	No	Significance level for confidence intervals and tests.
`treat`	Yes	Treatment indicator or exposure variable.
`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.
`covariates`	No	Measured confounders to condition on.
`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?

The description adds substantial behavioral context beyond the readOnlyHint annotation: it states assumptions, failure modes, typical minimum N, and recommended follow-up actions. This information is not present in annotations and helps an agent understand what to expect and how to react.

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 compact yet comprehensive, using a structured format (assumptions, pre-conditions, failure modes, alternatives, typical N) that front-loads the method name and key context. Every sentence adds value without redundancy.

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?

Given the tool's moderate complexity and the presence of a full output schema, the description covers all critical aspects: method identity, assumptions, preconditions, failure modes, alternatives, and sample size guidance. Nothing essential is missing for an agent to call it correctly.

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 all parameters are well-documented. The description adds minimal extra parameter semantics—it references the treatment column and negative-control outcome in the preconditions, but this aligns with schema descriptions. The baseline of 3 applies since the schema already handles parameter documentation.

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 tool as 'Lipsitch-style NCO calibration' and specifies its purpose (calibrating against a negative-control outcome). It distinguishes itself from sibling tools by naming alternatives (negative_control_exposure, sensemakr, evalue), making the tool's unique role apparent.

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 states pre-conditions (data has a negative-control outcome and treatment column), failure modes (coefficient differs from zero indicates residual confounding), and suggests actions (condition on more covariates or run sensitivity analysis). It also lists explicit alternatives, giving an agent clear guidance on when to select this tool versus others.

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

Deploy Server