Causal Decision Agent

Overview Schema Source Related Servers Discussions Admin

bvar

Read-only

Estimate Bayesian VAR models with Minnesota prior to analyze dynamic relationships and forecast multivariate time series.

Instructions

Bayesian VAR with Minnesota (Litterman) prior. Validation: validated evidence tier (known-truth, reference, external-parity, or Monte Carlo artifact).

Input Schema

TableJSON Schema

Name	Required	Description	Default
`lags`	No	lags parameter (int).
`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
`lambda1`	No	Overall tightness (smaller = stronger shrinkage toward RW).
`lambda2`	No	Cross-variable shrinkage relative to own-lag.
`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.
`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

C2.9/5.0

Behavior2/5

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

The description adds nothing about runtime behavior, side effects, or computational load beyond the readOnlyHint annotation. The 'validated evidence tier' note is about the tool's validation status, not its behavioral characteristics, so the agent gains no new disclosure.

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 a single sentence with no fluff, earning high marks for brevity. However, it is so sparse that it under-specifies the tool's purpose and behavior, so it does not fully earn its place as a standalone description.

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 complex Bayesian VAR with 9 parameters and an output schema (content unknown), the description is inadequate. It does not mention output interpretation, convergence diagnostics, or when to prefer this over simpler alternatives. The agent would need to inspect the schema or rely on prior knowledge.

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 already provides 100% coverage of all 9 parameters with descriptions. The tool description adds no extra context about parameter interactions, typical ranges, or how lambda1/lambda2 affect the prior. Baseline 3 is appropriate given full schema coverage.

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 clearly identifies the tool as fitting a Bayesian VAR with a Minnesota (Litterman) prior, which is a specific model and distinguishes it from the frequentist 'var' sibling. However, it omits what the tool actually produces (e.g., coefficient estimates, forecasts) and gives no hint of typical use cases.

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?

There is no guidance on when to use bvar versus other time-series tools like var, arima, or irf. No mention of alternatives, exclusions, or conditions that would make bvar the preferred choice.

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

Deploy Server