Causal Decision Agent

Overview Schema Source Related Servers Discussions Admin

tobit

Read-only

Fit a censored regression model for outcomes with known lower/upper thresholds, yielding coefficient estimates and confidence intervals to guide data-driven decisions.

Instructions

Tobit model for censored dependent variables. Validation: certified parity evidence. Assumptions: Latent outcome is linear in covariates with normally distributed errors; Censoring threshold is known and exogenous. Pre-conditions: Outcome censoring point and censoring direction are known; Covariates are numeric or properly encoded. Failure modes: MLE fails to converge or sigma is near zero -> Rescale covariates, simplify the model, or compare with censored quantile alternatives. Alternatives: sp.qreg, sp.regress. Typical minimum N: 100.

Input Schema

TableJSON Schema

Name	Required	Description	Default
`x`	Yes	Regressors
`y`	Yes	Censored outcome variable
`ll`	No	Lower censoring limit (set -inf for none)
`ul`	No	Upper censoring limit (default: none)
`alpha`	No	Significance level for confidence intervals
`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
`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

A3.9/5.0

Behavior4/5

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

Annotations already provide readOnlyHint=true, so the bar is lower. The description adds behavioral context: failure modes (MLE fails to converge, sigma near zero) with concrete remedies, and assumptions about the latent outcome. This goes beyond what annotations alone convey. No contradiction.

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 compact and logically structured with labeled sections (Validation, Assumptions, Pre-conditions, Failure modes, Alternatives, Typical minimum N). Every sentence adds distinct, useful information without fluff.

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

Completeness4/5

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

For a complex statistical tool with 11 parameters and an output schema, the description covers assumptions, pre-conditions, failure modes, alternatives, and sample size guidance. This is sufficient for an agent to decide whether to use the tool and what to do on failure. The output schema handles return-value details.

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 schema descriptions cover 100% of the 11 parameters, so the baseline is 3. The description adds only high-level pre-conditions (e.g., 'Covariates are numeric or properly encoded'), but does not elaborate on individual parameters beyond what the schema already states.

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 states a specific verb+resource: 'Tobit model for censored dependent variables.' It clearly identifies what the tool does, but it does not explicitly differentiate from sibling tools like truncreg or hurdle, despite naming alternatives (sp.qreg, sp.regress).

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

Usage Guidelines4/5

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

The description lists alternatives (sp.qreg, sp.regress) and gives pre-conditions (known censoring point and direction) and failure modes (MLE non-convergence) that imply when to use the tool and when to switch. It does not explicitly state 'use this when X, use sp.qreg when Y', but the conditions are clear enough.

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

Deploy Server