Causal Decision Agent

Overview Schema Source Related Servers Discussions Admin

mlogit

Read-only

Estimates multinomial logistic regression for categorical outcomes with more than two categories via maximum likelihood, providing coefficients, diagnostics, and parity validation evidence.

Instructions

Multinomial logit for J > 2 unordered categories via MLE. Validation: certified parity evidence.

Input Schema

TableJSON Schema

Name	Required	Description	Default
`x`	No	Regressors.
`y`	No	Dependent variable (categorical, integer-coded).
`rrr`	No	Report Relative Risk Ratios (exp(beta)) instead of coefficients.
`tol`	No	Numerical convergence tolerance.
`base`	No	Base / reference category (index into sorted unique values).
`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"`` / ``"HC1"`` for Huber-White sandwich SE.	nonrobust
`cluster`	No	Cluster variable for clustered SE.
`formula`	No	Formula ``"y ~ x1 + x2"``.
`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

B3.4/5.0

Behavior3/5

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

Annotations already declare readOnlyHint=true and openWorldHint=false, covering safety and external dependencies. The description adds a cryptic 'Validation: certified parity evidence' claim, which is not clearly explained and does not disclose behaviors like return format, errors, or prerequisites. It does not contradict annotations.

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 very brief—two sentences. The first sentence is front-loaded and clearly states the purpose. However, the second sentence about 'Validation: certified parity evidence' is vague and may not earn its place without more context.

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?

Although the schema is comprehensive with 16 parameters and an output schema, the description lacks contextual information about typical workflows, data requirements, or when to choose this tool among many related alternatives. It is minimally adequate but does not fully support an agent's decision-making.

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 coverage is 100%, with every parameter described in detail. The description adds no parameter semantics beyond the schema, so the baseline of 3 is appropriate.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the model type (multinomial logit), scope (J > 2 unordered categories), and estimation method (MLE). This distinguishes it from binary logit (logit), ordered logit (ologit), and conditional logit (clogit), which are common siblings.

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?

No guidance is provided on when to use this tool versus alternatives. The description does not mention when mlogit is appropriate (e.g., outcome has 3+ unordered categories) or when to choose other tools like mixlogit or clogit. This is a significant gap given the large sibling set.

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

Deploy Server