Causal Decision Agent

Overview Schema Source Related Servers Discussions Admin

demeaned_synth

Read-only

Estimates causal effects by de-meaning pre-treatment outcomes to construct a synthetic control from donor units, then measures post-treatment divergence.

Instructions

De-meaned / De-trended Synthetic Control Method. Assumptions: A convex (or regularized) combination of donor units reproduces the treated unit's pre-treatment outcome path; No interference: the treatment does not affect the donor units (SUTVA); No anticipation before the treatment date. Pre-conditions: Panel of one or more treated units plus an untreated donor pool, observed over time; Pre-treatment window long enough to fit donor weights (rule of thumb: more pre-periods than donors used); Outcome observed for every unit in every period. Failure modes: Large pre-treatment RMSPE -- the synthetic unit fails to track the treated unit before treatment -> Add donors / predictors, lengthen the pre-period, or use a bias-corrected estimator (sdid, augsynth); Placebo / permutation inference shows the estimate is not extreme relative to donors -> Report the placebo distribution honestly; the effect may not be distinguishable from noise. Alternatives: sp.sdid, sp.augsynth, sp.gsynth, sp.callaway_santanna. Typical minimum N: 15.

Input Schema

TableJSON Schema

Name	Required	Description	Default
`time`	Yes	Time period column.
`unit`	Yes	Unit identifier column.
`alpha`	No	Significance level.
`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
`outcome`	Yes	Outcome variable name.
`placebo`	No	Run in-space placebo inference.
`variant`	No	* ``'demeaned'`` -- subtract unit-level pre-treatment means. * ``'detrended'`` -- subtract unit-level linear time trends.	demeaned
`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.
`covariates`	No	Additional covariates to match on.
`data_columns`	No	Optional column projection. Parquet/Feather/Stata loaders honour this for fast partial reads.
`penalization`	No	Ridge penalty on weights.
`treated_unit`	Yes	Identifier of the treated unit.
`data_sample_n`	No	Optional uniform random subsample size (seed=0, deterministic) — useful on huge panels.
`treatment_time`	Yes	First treatment period (inclusive).

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

A4.1/5.0

Behavior4/5

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

Beyond the readOnlyHint annotation, the description discloses methodological assumptions (SUTVA, no anticipation) and failure modes, which inform the agent about the tool's limitations and expected behavior. It also clarifies the de-meaning/de-trending operation tied to the variant parameter. 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 is organized into labeled sections (Assumptions, Pre-conditions, Failure modes, Alternatives, Typical minimum N), making it scannable and well-structured. Every sentence contributes actionable information, though it is somewhat long. It is appropriately sized for a complex causal inference tool.

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

Completeness4/5

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

It covers assumptions, data requirements, failure modes with remedies, alternatives, and a minimum N heuristic—comprehensive for tool selection and invocation. With an output schema present, it does not need to describe return values. A minor omission is an explicit statement of the estimand (e.g., ATT), but that is implicit for synthetic control methods.

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 16 parameters are already documented in the schema. The description adds no parameter-specific details beyond the implied variant from 'De-meaned / De-trended', which the schema already covers. It meets the baseline but does not go beyond it.

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 states it is a 'De-meaned / De-trended Synthetic Control Method', clearly identifying the tool's purpose. It also lists assumptions and pre-conditions that further clarify what it does. However, it does not explicitly differentiate itself from sibling synthetic-control tools beyond naming alternatives.

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

Usage Guidelines5/5

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

The description provides explicit pre-conditions (e.g., pre-treatment window long enough, outcome observed for every unit) and failure modes with concrete remedies (e.g., add donors or use sdid/augsynth). It also names alternative tools and gives a 'Typical minimum N' heuristic, giving an agent strong guidance on when to use this tool versus others.

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

Deploy Server