Causal Decision Agent

Overview Schema Source Related Servers Discussions Admin

ppi_mean

Read-only

Estimate a population mean by combining gold-standard labels with model predictions on labeled and unlabeled data, returning a confidence interval.

Instructions

Prediction-powered estimate of a population mean.

Input Schema

TableJSON Schema

Name	Required	Description	Default
`y`	Yes	Gold-standard (human) outcomes on the labeled sample.
`tune`	No	Use the PPI++ power-tuning weight ``lambda in [0, 1]``. ``False`` fixes ``lambda = 1`` (the original PPI estimator).
`yhat`	Yes	Model predictions on 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
`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.
`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.
`yhat_unlabeled`	Yes	Model predictions on 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

C2.9/5.0

Behavior2/5

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

The annotation readOnlyHint=true already covers the read-only nature, so the description needn't repeat safety info. However, the description adds no behavioral context: no mention of requiring labeled + unlabeled data, the role of the tuning parameter, or any assumptions. It contributes nothing beyond what the annotation and schema provide.

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 a single front-loaded phrase with no filler; each word contributes to the core purpose. It is minimal but not wasteful. Its brevity limits context, but that is penalized under other dimensions.

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?

For a tool with 11 parameters, an output schema, and a vast sibling set, one line is insufficient context. The description omits the data requirements, the meaning of 'prediction-powered', and any distinction from ppi_ols. An agent would need to rely entirely on the schema and output schema to make a correct invocation.

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 11 parameters (y, yhat, yhat_unlabeled, tune, alpha, detail, as_handle, etc.) are already documented in the input schema. The description adds no parameter-level meaning, so the baseline 3 is appropriate.

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 states the tool estimates a population mean using prediction-powered inference, a specific verb-resource pair. The method term 'prediction-powered' helps distinguish it from other estimation tools, though it doesn't name siblings explicitly. It is not a tautology and adds a method dimension.

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 this tool versus alternatives like ppi_ols or direct_method. There are no stated conditions, exclusions, or recommended contexts. With over 200 sibling tools, an agent must inspect schemas of multiple candidates to decide.

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

Deploy Server