Causal Decision Agent

Overview Schema Source Related Servers Discussions Admin

mepoisson

Read-only

Run random-effects Poisson regression on grouped count data to estimate fixed and random effects, with optional offsets and diagnostics for causal analysis.

Instructions

Random-effects Poisson regression (Stata mepoisson).

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

A3.5/5.0

Behavior3/5

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

Annotations already declare the operation read-only, and the description adds the model-family detail and Stata-equivalent label. It does not describe convergence behavior, random-effects parameterization, or edge cases, but with the annotations and output schema present the core safety profile is covered.

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

Conciseness5/5

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

A single, front-loaded sentence states the estimator and its Stata alias without any filler or redundancy. It is as concise as possible while adding value beyond the tool name.

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 detailed input schema, output schema, and annotations cover invocation and return shape, and the method label conveys the statistical context. However, with many overlapping siblings (meglm, xtnbreg, poisson, fepois), the lack of explicit selection criteria keeps it from being fully complete.

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?

The description contributes no parameter information, but the input schema has descriptions for all 12 parameters (100% coverage), so the schema carries the parameter-semantics burden. Even if a few schema entries are terse (e.g., nAGQ), the description is not required to compensate under the baseline.

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 clearly identifies the estimator as random-effects Poisson regression and maps it to the Stata `mepoisson` command, so the agent knows exactly what model family is being requested. It is distinct from the plain `poisson` sibling by the 'random-effects' qualifier, though it doesn't spell out an action verb like 'fit' or 'estimate'.

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

Usage Guidelines3/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Usage context is only implied by the method name: Poisson implies count outcomes and random-effects implies clustered/grouped data. The description does not name alternatives such as `poisson`, `meglm`, `xtnbreg`, or exclusion conditions like overdispersion, so the agent gets no explicit routing guidance.

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

Deploy Server