Causal Decision Agent

Overview Schema Source Related Servers Discussions Admin

gap_closing

Read-only

Measures the counterfactual outcome gap between groups after equalizing covariate distributions, producing certified parity evidence to support fairness decisions.

Instructions

Counterfactual gap after equalising covariate distributions. Validation: certified parity evidence.

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.
`trim`	No	trim parameter (float).
`alpha`	No	Significance level for confidence intervals and tests.
`group`	Yes	Group or cohort identifier.
`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
`method`	No	AIPW is doubly robust (recommended).	aipw
`n_boot`	No	Number of bootstrap replications.
`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://.
`inference`	No	inference parameter (str).	analytical
`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.
`target_dist`	No	- 1: shift Group A's covariate distribution to match Group B's - 0: shift Group B's to match Group A's
`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

C2.2/5.0

Behavior2/5

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

The annotations already declare readOnlyHint=true, so the read-only nature is covered. The description adds a cryptic 'Validation: certified parity evidence' which hints at some validation output but does not explain what it means or what other behaviors to expect (e.g., output format, dependencies). It provides minimal additional context beyond the annotations.

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 description is extremely short (a single sentence), which is concise but at the cost of substance. For a tool with 16 parameters and a complex operation, this is under-specification rather than effective conciseness. There is no structure or front-loading of key information; it reads as a cryptic summary.

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 complexity (16 params, output schema exists), the description is incomplete. It does not explain what the 'counterfactual gap' means, how to interpret results, or what the tool is designed for. The output schema may cover return values, but the purpose and usage context are severely lacking. An agent would struggle to know when and how to call this tool 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 16 parameters have descriptions in the schema. Per the rubric, the baseline is 3 when the schema covers parameters. The tool description itself adds no parameter-level meaning, but the schema handles that. The description does not clarify how parameters like target_dist or method fit into the overall goal, but this is a minor gap given the schema's thoroughness.

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 states the tool computes a 'counterfactual gap after equalising covariate distributions', which gives a general sense of the operation, but it is vague and does not specify the exact estimator or context (e.g., causal inference, fairness). It is not a tautology, but it lacks precision and does not distinguish it from many sibling tools that also deal with disparities or counterfactuals.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines1/5

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 alternatives. The description does not mention any conditions, prerequisites, or exclusions. An agent cannot determine when gap_closing is the right choice among the dozens of related tools without further information.

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

Deploy Server