Causal Decision Agent

Overview Schema Source Related Servers Discussions Admin

menbreg

Read-only

Apply random-effects negative-binomial regression to model overdispersed count outcomes with group/cohort random intercepts, producing coefficients and diagnostics for causal decision-making.

Instructions

Random-effects negative-binomial regression (Stata menbreg).

Input Schema

TableJSON Schema

Name	Required	Description	Default
`y`	Yes	Outcome variable column name or outcome array.
`nAGQ`	No	nAGQ parameter (int).
`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
`offset`	No	Offset term or offset column.
`x_fixed`	Yes	x_fixed parameter (Sequence[str]).
`x_random`	No	x_random parameter (Optional[Sequence[str]]).
`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.
`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

B3.2/5.0

Behavior3/5

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

The readOnlyHint annotation already signals a safe, non-mutating operation, and the description is consistent with that. The description adds no extra behavioral context beyond the model name, such as whether fitting caches results or how the detail payload varies, but the schema documents the as_handle and detail behaviors.

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

Conciseness4/5

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

The description is extremely compact and front-loads the key model family. The parenthetical '(Stata menbreg)' is near-redundant with the tool name but is not harmful.

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?

The rich input schema and output schema cover data handling, parameter meanings, and return behavior, so the description does not need to repeat them. However, the description leaves an important selection ambiguity unresolved: xtnbreg is near-identical in name and model family, and the description never clarifies that menbreg is the mixed/multilevel variant.

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 parameter documentation carries the burden and the description correctly does not duplicate it. Several schema descriptions are thin (e.g., 'nAGQ parameter (int).'), but the baseline for high coverage is still 3.

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 phrase 'Random-effects negative-binomial regression (Stata menbreg)' identifies the statistical model and the tool's Stata heritage, which is clear enough for an expert agent. There is no explicit verb like 'fits' or 'estimates', and it does not distinguish menbreg from the very similar sibling xtnbreg.

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?

The description gives no guidance on when to use menbreg versus alternatives such as xtnbreg, nbreg, or meglm. No context, prerequisites, or exclusion criteria are provided, so an agent must rely on prior knowledge to select this tool correctly.

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

Deploy Server