Causal Decision Agent

Overview Schema Source Related Servers Discussions Admin

yun_nonlinear

Read-only

Decompose group differences in binary outcomes via Bauer-Sinning nonlinear Oaxaca-Blinder, fitting logit or probit to separate explained from unexplained contributions.

Instructions

Bauer-Sinning (2008) nonlinear Oaxaca-Blinder decomposition with

Input Schema

TableJSON Schema

Name	Required	Description	Default
`x`	Yes	Primary running variable, regressor, or feature input for this estimator.
`y`	Yes	Outcome variable column name or outcome array.
`group`	Yes	Group or cohort identifier.
`model`	No	Model variant or parameterisation to fit.	logit
`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
`variant`	No	variant parameter (str).	yun
`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://.
`reference`	No	reference parameter (int).
`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

C2.4/5.0

Behavior2/5

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

The annotations already signal readOnlyHint=true, and the description adds no behavioral context beyond naming the method. It does not disclose what the call returns, whether results are cached, what model variants matter, or any operational side effects. There is no annotation contradiction, but the description carries almost no disclosure burden.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness2/5

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

The text is brief, but it is not a complete or well-structured sentence—the trailing 'with' indicates truncation. This is under-specification rather than disciplined conciseness.

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 12-parameter nonlinear decomposition estimator with many close sibling tools, the description is far too incomplete. An agent cannot tell why yun_nonlinear is preferred over bauer_sinning, what output shape to expect, or which options are relevant. The truncated one-line description is not sufficient despite the rich schema.

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 baseline for this dimension is 3. The description contributes no parameter-level meaning; all semantics are left to fields like model, detail, reference, and as_handle in the schema.

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

Purpose3/5

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

The description names a concrete method—'Bauer-Sinning (2008) nonlinear Oaxaca-Blinder decomposition'—so the technical purpose is recognizable. However, it is a dangling noun phrase cut off at 'with', has no explicit verb, and does not distinguish this tool from the sibling bauer_sinning or nearby oaxaca/fairlie tools.

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?

There is no guidance about when to use this tool instead of alternatives. Given many close siblings such as bauer_sinning, oaxaca, dfl_decompose, and fairlie, the description provides no selection criteria, exclusions, or prerequisites.

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

Deploy Server