Causal Decision Agent

Overview Schema Source Related Servers Discussions Admin

panel_probit

Read-only

Run panel probit analysis on binary outcome data, returning coefficient estimates, diagnostics, and action-ready next steps for evidence-based decision audits.

Instructions

Panel probit model. Validation: certified parity evidence.

Input Schema

TableJSON Schema

Name	Required	Description	Default
`x`	Yes	Regressors.
`y`	Yes	Binary dependent variable (0/1).
`id`	No	Unit and time identifier columns.	id
`tol`	No	Gradient tolerance.
`time`	No	Unit and time identifier columns.	time
`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
`method`	No	're' (random effects) or 'cre' (Mundlak). FE probit not supported (incidental parameters problem).	re
`robust`	No	'nonrobust' or 'robust'.	nonrobust
`cluster`	No	Column for cluster-robust SEs.
`maxiter`	No	Maximum optimizer iterations.
`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.
`n_quadrature`	No	Gauss-Hermite quadrature points.
`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

D1.7/5.0

Behavior1/5

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

Annotations declare readOnlyHint=true and openWorldHint=false, so the agent knows it is a read-only operation. The description adds no behavioral context beyond this—no mention of output structure, side effects, or validation behavior. The phrase 'certified parity evidence' is ambiguous and does not disclose what the tool does with data.

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 short but lacks substance. It consists of two fragments ('Panel probit model.' and 'Validation: certified parity evidence.'), the second being unclear. This is under-specification rather than effective conciseness.

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?

Given the tool has 17 parameters, an output schema, and many siblings, this description is severely incomplete. It does not explain the model's assumptions (e.g., random effects vs fixed effects), the meaning of 'certified parity evidence', or how to chain with as_handle. An agent would have to rely entirely on the schema.

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, so all 17 parameters are documented. The description adds nothing 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.

Purpose2/5

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

The description is a noun phrase 'Panel probit model' without an explicit verb like 'estimates' or 'fits'. It identifies the model type but does not state the action performed, nor does it differentiate from siblings such as probit or panel_logit. This is vague but not a tautology.

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 this tool versus alternatives like probit, logit, or panel_logit. No conditions, prerequisites, or exclusions are mentioned. The cryptic phrase 'certified parity evidence' does not clarify usage.

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

Deploy Server