Causal Decision Agent

Overview Schema Source Related Servers Discussions Admin

hurdle

Read-only

Fit a two-part count model to data with excess zeros and generate certified parity evidence for rollout or hold verdicts.

Instructions

Hurdle (two-part) model for count data. Validation: certified parity evidence.

Input Schema

TableJSON Schema

Name	Required	Description	Default
`x`	No	Regressors (used for both hurdle and count parts).
`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	Robust standard-error or covariance estimator option.	nonrobust
`cluster`	No	Cluster identifier column for clustered standard errors.
`formula`	No	Patsy-style formula.
`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.
`count_model`	No	Count distribution: "poisson" or "negbin".	poisson
`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

B3.1/5.0

Behavior3/5

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

Annotations already mark the operation as read-only, and the description adds the note 'Validation: certified parity evidence,' which hints at extra validation output. However, this is vague and does not explain what the validation covers or what side effects (e.g., as_handle caching) might occur. With annotations covering safety, the description provides modest additional context only.

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 two-sentence description is front-loaded with the model type and contains no redundant prose. It is slightly terse, but no sentence is wasted.

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

Completeness2/5

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

For a 15-parameter model-fitting tool with many related siblings, the description is too thin: it does not explain the hurdle model's data requirements, when it applies, or how it differs from zero-inflated alternatives. The output schema and annotations partially compensate, but an agent still lacks enough context to invoke this tool confidently.

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 input schema already documents all 15 parameters. The tool description itself adds no parameter-level information, matching the baseline of 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 description identifies the resource as a hurdle two-part model for count data, which clearly separates it from count-model siblings like poisson, nbreg, and zip_model. It lacks an explicit verb like 'fit' or 'estimate', but the model name plus count-data scope is sufficient for an agent to infer the operation.

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 choose a hurdle model over zero-inflated or plain count models, nor does it name any alternative tools. There are no prerequisites or exclusions stated.

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

Deploy Server