Causal Decision Agent

by vikranthviki

Overview Schema Source Related Servers Discussions Admin

Python

Local

garch

Read-only

Fit GARCH(p,q) models to return series via conditional Gaussian MLE for volatility estimation and diagnostic analysis.

Instructions

Fit GARCH(p,q) by conditional Gaussian MLE. Validation: validated evidence tier (known-truth, reference, external-parity, or Monte Carlo artifact).

Input Schema

TableJSON Schema

Name	Required	Description	Default
`p`	No	Number of GARCH (lagged sigma2) terms.
`q`	No	Number of ARCH (lagged epsilon2) terms.
`y`	Yes	Return series (or log-return, etc.).
`mean`	No	Estimate a constant mean mu; if False, mu = 0.
`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
`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

B3.3/5.0

Behavior3/5

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

Annotations already provide readOnlyHint=true and openWorldHint=false, covering the safety profile. The description adds only the estimation method (Gaussian MLE) and a meta-note about validation tiers, which is not behavioral. No contradiction with annotations, but little additional behavioral 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 first sentence is crisp and front-loaded with the core purpose. The second sentence about validation tier is tangential and arguably not needed for tool selection, but the overall description remains short and scannable.

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?

With 10 parameters and no explanation of when to use GARCH, prerequisites (e.g., stationary time series), or relationships to sibling volatility models, the description is incomplete for an agent to plan a call confidently. The output schema and annotations cover some gaps, but the usage context is missing.

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 all parameters are already documented in the schema. The description merely echoes p and q in the model notation and adds no semantic meaning beyond what the schema provides, matching the baseline for full schema coverage.

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 uses a specific verb ('Fit'), resource ('GARCH(p,q)'), and method ('conditional Gaussian MLE'), making the tool's purpose unmistakable. It clearly distinguishes garch from siblings like arima and var without needing to inspect their schemas.

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 GARCH versus alternative time-series tools (e.g., arima, var), no exclusions, and no prerequisites. The description only states what the tool does, not when an agent should choose it.

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

Deploy Server