Causal Decision Agent

Overview Schema Source Related Servers Discussions Admin

sureg

Read-only

Run seemingly unrelated regression on connected equations, returning coefficient tables, diagnostics, and validation evidence to support causal decision audits.

Instructions

Seemingly Unrelated Regression (SUR). Validation: certified parity evidence.

Input Schema

TableJSON Schema

Name	Required	Description	Default
`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
`method`	No	'ols' (equation-by-equation), 'fgls' (feasible GLS / SUR), 'iterative' (iterated SUR).	fgls
`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`	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://.
`equations`	Yes	Mapping from equation name to (dep_var, list_of_regressors).
`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

C2.8/5.0

Behavior2/5

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

Annotations declare readOnlyHint=true, so the operation is known to be read-only, but the description itself adds no behavioral detail. The phrase 'Validation: certified parity evidence' is cryptic and does not explain output behavior, error cases, or data requirements beyond what the schema already states.

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 short and the first sentence is front-loaded. However, the second sentence, 'Validation: certified parity evidence,' is not clearly actionable and does not earn its place as useful guidance.

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?

Although the input schema is detailed and an output schema exists, the description leaves out essential selection context for a complex econometric tool. An agent selecting among many regression-family siblings would need to know when SUR is appropriate and what the validation claim means.

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 schema already documents all 11 parameters, including defaults and enums. The description adds no parameter-level meaning, so the baseline score of 3 is appropriate.

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 exact estimator ('Seemingly Unrelated Regression (SUR)') and expands the tool name, so an agent can tell this is a SUR procedure. However, it uses no action verb and does not explicitly contrast it with related siblings such as panel_fgls or three_sls.

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 provides no guidance on when to use sureg versus alternatives like regress, panel_fgls, or three_sls. There are no explicit when-to-use conditions, 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