Causal Decision Agent

Overview Schema Source Related Servers Discussions Admin

betareg

Read-only

Fit beta regression models for outcomes in (0,1), with optional precision regressors, robust standard errors, and cluster-robust inference to support evidence-based decisions.

Instructions

Beta regression (Ferrari & Cribari-Neto 2004). Validation: certified parity evidence.

Input Schema

TableJSON Schema

Name	Required	Description	Default
`x`	No	Regressors for the mean equation.
`y`	No	Outcome in (0, 1).
`z`	No	Regressors for the precision equation. If None, constant precision.
`tol`	No	Numerical convergence tolerance.
`link`	No	Link for mean: 'logit', 'probit', 'cloglog'.	logit
`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	Robust standard-error or covariance estimator option.	nonrobust
`cluster`	No	Cluster identifier column for clustered standard errors.
`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

C2.2/5.0

Behavior1/5

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

The annotations declare readOnlyHint=true and openWorldHint=false, so the tool is known to be read-only. The description adds only a validation claim ('certified parity evidence') but discloses no behavioral aspects such as computational cost, assumptions, or response structure. It does not contradict annotations, but adds negligible behavioral transparency beyond them.

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 brief (two short sentences), but the brevity is under-specification rather than efficient conciseness. The first sentence simply restates the tool's name in a verbose form, and the second is a vague validation claim. It does not provide essential information in a structured or front-loaded manner.

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

Completeness1/5

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

For a tool with 15 parameters and no required ones, the description is grossly inadequate. It does not explain the overall workflow, expected inputs, output format, or how it relates to similar tools. Despite the schema having descriptions, the high-level context is missing, leaving an agent unable to determine when or how to invoke it effectively.

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 input schema has 100% description coverage for all 15 parameters, so the schema already documents each parameter. The description adds no additional meaning or context about parameters, such as the role of 'x', 'y', and 'z' or the 'detail' levels. Given the high schema coverage, a baseline of 3 is appropriate, but the description does not enhance understanding beyond the schema.

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 states the tool performs beta regression and cites the reference (Ferrari & Cribari-Neto 2004). It identifies the method and its intended use for bounded outcomes. However, it does not differentiate from other regression siblings like 'glm' or 'logit', relying on the name alone to imply the distinction.

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 beta regression versus alternatives. The description does not mention conditions such as outcome in (0,1) or when to prefer it over other models, nor does it exclude any scenarios. An agent would have to infer from the name and schema that it is for bounded continuous outcomes.

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

Deploy Server