Causal Decision Agent

Overview Schema Source Related Servers Discussions Admin

probit

Read-only

Estimate binary outcome models via maximum likelihood, returning coefficients, diagnostics, and evidence for causal decisions.

Instructions

Probit regression via maximum likelihood. Validation: certified parity evidence.

Input Schema

TableJSON Schema

Name	Required	Description	Default
`x`	No	Regressor names (alternative to formula).
`y`	No	Dependent variable name (alternative to formula).
`tol`	No	Convergence tolerance on log-likelihood change.
`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
`robust`	No	``'nonrobust'`` for MLE SE, ``'hc1'`` / ``'robust'`` for sandwich SE.	nonrobust
`cluster`	No	Column name for clustered standard errors.
`formula`	No	Formula like ``"y ~ x1 + x2"``.
`maxiter`	No	Maximum Newton-Raphson iterations.
`weights`	No	Column name for frequency/analytic weights.
`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.
`at_values`	No	Variable values for ``marginal_effects='at'``.
`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.
`marginal_effects`	No	``'average'`` (AME), ``'mean'`` (MEM), or ``'at'`` (MER).

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

C2.5/5.0

Behavior2/5

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

Annotations declare readOnlyHint=true, so the description does not contradict them. It adds 'Validation: certified parity evidence,' but without explaining what parity evidence means or what the tool does beyond fitting. For a read-only tool, this is minimal added context; the cryptic phrase does not clarify expected behavior or outputs.

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

Conciseness3/5

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

The description is two sentences and front-loaded with the main purpose. However, the second sentence is cryptic and likely unhelpful to an agent. It is concise but under-specified, which is not the same as good structure.

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?

With 17 parameters, an output schema, and a large sibling set, the description is far too sparse. It does not explain the tool's role in the workflow, data preparation, validation behavior, or when to prefer it over related tools. The schema compensates for parameter semantics but not for overall context.

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%, meaning all 17 parameters are already described in the schema. The description adds no parameter-level meaning beyond the schema, so it stays at the baseline 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 states 'Probit regression via maximum likelihood', giving a specific verb and statistical resource. The name itself distinguishes it from oprobit/logit, but the description does not explicitly contrast with sibling tools like logit or oprobit, so it earns a 4 rather than 5.

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 probit versus logit, oprobit, or other alternatives. The only extra sentence, 'Validation: certified parity evidence,' offers no selection criteria, prerequisites, or exclusions.

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

Deploy Server