Causal Decision Agent

Overview Schema Source Related Servers Discussions Admin

causal_impact

Read-only

Quantify the causal effect of an intervention on a time series by modeling a counterfactual from pre-period data. Returns point estimates, posterior intervals, and diagnostics for decisions.

Instructions

Bayesian structural time series for causal impact analysis. Assumptions: No simultaneous shocks affect treated and control series differently at intervention; Pre-period relationship extrapolates into the post-period absent treatment. Pre-conditions: Observed time series has a clearly defined intervention date; Pre-intervention period is long enough to fit the counterfactual model. Failure modes: Poor pre-period fit or unstable posterior predictive interval -> Add controls, lengthen the pre-period, or use synthetic control as a robustness check. Alternatives: sp.synth, sp.sequential_sdid, sp.local_projections. Typical minimum N: 30.

Input Schema

TableJSON Schema

Name	Required	Description	Default
`y`	Yes	Outcome time-series column
`time`	Yes	Time / date column
`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`	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.
`intervention_time`	Yes	Date/index of intervention

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

A4.4/5.0

Behavior5/5

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

Assumptions about simultaneous shocks and pre/post relationship extrapolation clarify the causal identification logic. Failure modes (poor pre-period fit, unstable posterior predictive interval) plus suggested actions (add controls, lengthen pre-period, synthetic control) disclose behavior beyond the readOnlyHint annotation. No contradiction with 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 uses labeled sections (Assumptions, Pre-conditions, Failure modes, Alternatives, Typical minimum N) to organize dense information efficiently. It is longer than some but every sentence earns its place; no fluff.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a complex causal inference tool, the description covers assumptions, preconditions, failure modes, alternatives, and sample-size guidance. With an output schema present, return-value details are unnecessary. The description is complete for an agent to decide when to call it and what inputs are required.

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 every parameter is already documented in the schema (e.g., intervention_time, y, time). The description adds no parameter-specific syntax or format details beyond the schema. Baseline 3 applies.

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 states a specific method ('Bayesian structural time series') and its purpose ('causal impact analysis'). It names three alternatives (sp.synth, sp.sequential_sdid, sp.local_projections), distinguishing it from sibling tools. This meets the 5 criterion: specific method + resource and sibling differentiation.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Pre-conditions define when the tool is appropriate: a clearly defined intervention date and a long enough pre-intervention period. Failure modes and recommended remedies give further situational guidance. However, alternatives are merely listed without explicit conditions for choosing among them, so it stops short of a 5.

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

Deploy Server