Causal Decision Agent

Overview Schema Source Related Servers Discussions Admin

fairlie

Read-only

Decompose group differences in binary outcomes using nonlinear decomposition to quantify each predictor's contribution to the observed gap.

Instructions

Fairlie (2005) nonlinear decomposition for binary outcomes. Validation: validated evidence tier (known-truth, reference, external-parity, or Monte Carlo artifact).

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.
`seed`	No	Random seed for reproducible stochastic steps.
`group`	Yes	Group or cohort identifier.
`model`	No	Model variant or parameterisation to fit.	logit
`n_sim`	No	Number of sim.
`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://.
`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

B3/5.0

Behavior2/5

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

Annotations declare readOnlyHint=true, which covers the safety profile. The description adds only a cryptic note about 'validated evidence tier' which does not describe runtime behavior, return format, or potential errors. It does not contradict annotations, but it adds little beyond them, so transparency is limited.

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

Conciseness3/5

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

The description is concise (two sentences) and front-loads the purpose. However, the second sentence about validation is vague and does not aid usage; it could be removed or clarified. The structure is not inefficient, but it does not maximize usefulness for an agent.

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?

Given the tool has 13 parameters and sits among dozens of decomposition tools, the description is inadequate. It lacks usage guidelines, comparison to alternatives, description of output or next steps, and any contextual cues that would help an agent decide to invoke it. The output schema exists but the description does not leverage it.

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 every parameter is documented in the input schema itself. The tool description provides no additional parameter-level insight. Since the schema does the heavy lifting, the baseline of 3 is appropriate; the description neither adds nor detracts from parameter understanding.

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 states the tool performs a Fairlie (2005) nonlinear decomposition for binary outcomes. This is a specific verb (decompose) applied to a specific method (Fairlie) and outcome type (binary), which distinguishes it from linear (Oaxaca) or distributional (Melly) decomposition tools. It names the method and the context, making its purpose unambiguous.

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 on when to use this tool versus the many decomposition siblings (e.g., dfl_decompose, oaxaca, melly_decompose). The description does not mention any conditions, prerequisites, or when to avoid it. An agent must rely on the method name alone to decide, which is insufficient given the large family of similar tools.

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

Deploy Server