Causal Decision Agent

Overview Schema Source Related Servers Discussions Admin

ppi_ols

Read-only

Run prediction-powered OLS: combine a labeled audit sample with model predictions on unlabeled data to obtain valid coefficient estimates and confidence intervals.

Instructions

Prediction-powered OLS with a labeled audit sample.

Input Schema

TableJSON Schema

Name	Required	Description	Default
`X`	Yes	Covariates for the labeled rows.
`y`	Yes	Gold-standard outcomes for the labeled rows.
`tune`	No	Per-coefficient PPI++ power tuning. ``False`` fixes ``lambda = 1``.
`yhat`	Yes	Model-predicted outcomes for the same labeled rows.
`alpha`	No	CI level (1 - alpha confidence).
`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
`target`	No	Which coefficient is the headline ``estimate``. Defaults to the first non-intercept term.
`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`	No	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.
`X_unlabeled`	Yes	Covariates for the unlabeled rows (same columns as ``X``).
`data_columns`	No	Optional column projection. Parquet/Feather/Stata loaders honour this for fast partial reads.
`add_intercept`	No	Prepend a constant column to both design matrices.
`data_sample_n`	No	Optional uniform random subsample size (seed=0, deterministic) — useful on huge panels.
`yhat_unlabeled`	Yes	Model-predicted outcomes for the unlabeled rows.

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

B3.3/5.0

Behavior3/5

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

Annotations already declare readOnlyHint=true, so the safety profile is covered. The description adds the contextual point that a labeled audit sample is used, which clarifies the method's data requirement, but it does not disclose further behavioral traits such as assumptions, output behavior, or chaining capabilities.

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?

A single sentence with no wasted words. It front-loads the method name and the key data requirement, making the description as concise as possible.

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

Completeness3/5

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

The schema is rich and fully documents parameters, and the output schema exists, so the description need not explain those. However, the tool is a complex statistical method among many siblings, and the one-sentence description does not provide enough context about when to choose it or how it fits into a workflow.

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 carries the full burden of documenting all 15 parameters. The description itself adds no parameter-level meaning beyond what the schema already provides, so the baseline score of 3 applies.

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

Purpose4/5

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

The description clearly identifies the tool as prediction-powered OLS using a labeled audit sample. It conveys the core method and data requirement, though it lacks a verb and does not explicitly differentiate it from the closely related ppi_mean sibling.

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 given on when to use ppi_ols versus alternatives such as ppi_mean, direct_method, or standard regression tools. The description states the method but provides no 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