zinb

Read-only

Fit a zero-inflated negative binomial regression to count data with excess zeros, providing coefficient estimates and diagnostics for evidence-backed business decisions.

Instructions

Zero-Inflated Negative Binomial (ZINB) regression via MLE. Validation: certified parity evidence.

Input Schema

TableJSON Schema

Name	Required	Description	Default
`x`	No	Count-equation regressors.
`y`	No	Dependent variable name.
`tol`	No	Numerical convergence tolerance.
`alpha`	No	Significance level for confidence intervals and tests.
`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
`robust`	No	Standard error type.	nonrobust
`cluster`	No	Cluster variable name.
`formula`	No	Patsy-style formula for the count equation.
`inflate`	No	Inflation-equation regressors. Default: same as count regressors.
`maxiter`	No	maxiter parameter (int).
`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.

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?

Annotations already declare readOnlyHint=true, and the description adds essentially no behavioral context beyond that. The phrase 'Validation: certified parity evidence' is obscure and does not meaningfully disclose behavior (e.g., fitting, caching via as_handle, or result payloads). No contradiction with annotations exists, but the description fails to enrich the safety/behavior profile.

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 appropriately brief and front-loads the main purpose. However, the second sentence 'Validation: certified parity evidence' is cryptic and does not earn its space — it likely confuses rather than informs an agent, so the conciseness does not translate to clarity.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness3/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With 15 parameters but 100% schema coverage and an output schema present, the description carries a lighter burden. It is adequate for identifying the model type but lacks the sibling differentiation and usage context needed to fully guide an agent choosing among the many count/zero-inflated regression tools in the sibling list.

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 parameters (x, y, tol, alpha, detail, robust, cluster, formula, inflate, etc.) are already documented in the schema. The description adds no extra meaning or usage nuance for any parameter, so the baseline of 3 applies.

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 estimator ('Zero-Inflated Negative Binomial (ZINB) regression via MLE') with a clear verb and resource, which distinguishes it from siblings like nbreg, zip_model, hurdle, and menbreg. However, the appended line 'Validation: certified parity evidence' is cryptic and adds no clarity about what the tool does.

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 choose ZINB over related count/inflation models (nbreg, zip_model, hurdle, menbreg) or when it is inappropriate (e.g., data without excess zeros). The description offers no context about prerequisites, data requirements, or selection conditions.

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

Deploy Server

Causal Decision Agent