Causal Decision Agent

Overview Schema Source Related Servers Discussions Admin

fisher_exact

Read-only

Run Fisher's exact randomization test to assess treatment effects with permutation-based p-values, supporting cluster or stratified designs and covariate adjustment for reproducible causal evidence.

Instructions

Fisher's exact randomization test with enhanced features. Validation: validated evidence tier (known-truth, reference, external-parity, or Monte Carlo artifact).

Input Schema

TableJSON Schema

Name	Required	Description	Default
`y`	Yes	Outcome variable name.
`seed`	No	Random seed for reproducibility.
`alpha`	No	Significance level for the Hodges-Lehmann confidence interval.
`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
`n_perm`	No	Number of random permutations.
`cluster`	No	Variable for cluster-level randomization (permute by cluster).
`controls`	No	Control variables for covariate-adjusted inference. When provided, the test statistic is computed on residuals from regressing Y on controls.
`stratify`	No	Variable for stratified permutation (permute within strata).
`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://.
`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.
`statistic`	No	Test statistic to use: - ``'ate'``: Average treatment effect (difference in means). - ``'ks'``: Kolmogorov-Smirnov statistic. - ``'rank_sum'``: Wilcoxon rank-sum statistic.	ate
`treatment`	Yes	Binary treatment variable name (0/1).
`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

C2.8/5.0

Behavior2/5

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

Annotations already declare readOnlyHint=true and openWorldHint=false, covering the safety profile. The description adds only a cryptic 'Validation: validated evidence tier (...)' fragment that reads like an output-field spec rather than behavioral disclosure — it does not explain permutation behavior, defaults, or consequences of the call. No contradiction with annotations, but almost no added value.

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 short and front-loaded with the main clause. However, the second sentence is a malformed field-style fragment ('Validation: ...') rather than prose, and 'with enhanced features' is content-free filler, so the brevity is not backed by clean structure.

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?

Despite an output schema and 15 configurable parameters (permutation count, stratification, clustering, statistic choice, controls), the description tells an agent almost nothing beyond the test's name. An agent is left to infer statistical behavior from parameter names, and the confusing validation sentence does not compensate for the missing behavioral and selection context.

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 fully documents all 15 parameters (defaults, enums, meanings) and earns the baseline. The description contributes nothing about parameters, but with full schema coverage the heavy lifting is already done.

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 names a specific statistical procedure — Fisher's exact randomization test — which is a concrete resource that distinguishes it from most of the ~300 sibling tools. However, it lacks an explicit verb ('performs', 'computes') and makes no direct contrast with near-siblings like ri_test, and 'with enhanced features' is vague filler.

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 such as ri_test, reset_test, or the many other inference/test tools in the sibling list. The second sentence ('Validation: ...') concerns output structure, not usage context, so an agent has no basis for choosing this over similar tests.

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

Deploy Server