Causal Decision Agent

Overview Schema Source Related Servers Discussions Admin

robust_synth

Read-only

Estimates causal treatment effects by constructing a synthetic control from donor units, then validates the fit with placebo inference and diagnostics to support go/no-go decisions.

Instructions

Robust / unconstrained Synthetic Control. 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	* ``'unconstrained'`` -- no sign / sum constraints; optional intercept. * ``'elastic_net'`` -- L1 + L2 penalty, no sign constraints. * ``'penalized'`` -- classic SCM constraints + elastic-net penalty.	unconstrained
`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://.
`intercept`	No	Fit an intercept (level shift). Only for unconstrained / elastic_net.
`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.
`l1_penalty`	No	Lasso (L1) penalty strength.
`l2_penalty`	No	Ridge (L2) penalty strength.
`data_columns`	No	Optional column projection. Parquet/Feather/Stata loaders honour this for fast partial reads.
`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.

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

A4.3/5.0

Behavior5/5

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

Beyond the readOnlyHint annotation, the description discloses key assumptions (SUTVA, no anticipation), failure modes (poor pre-treatment fit, non-extreme placebo estimates), and honest reporting guidance. This gives the agent interpretive context that annotations alone cannot provide.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is organized into labeled sections (assumptions, pre-conditions, failure modes, alternatives) and every sentence carries information. It is dense but not padded, and it front-loads the method identity.

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 estimator, it covers assumptions, data requirements, failure modes, alternatives, and minimum sample size. The output schema and detailed parameter descriptions cover the remaining API contract, leaving no critical gap for a caller.

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%, and the parameter descriptions are already detailed with defaults, enums, and payload-depth semantics. The tool description itself does not add parameter-specific meaning, so the baseline 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 clearly identifies the tool as 'Robust / unconstrained Synthetic Control' and distinguishes it from sibling estimators by naming concrete alternatives. It lacks an explicit verb like 'estimates a treatment effect,' but the assumptions and preconditions make the purpose unambiguous.

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?

The description provides explicit assumptions, pre-conditions, failure modes, and alternatives, including conditional guidance to switch to sdid/augsynth when pre-treatment RMSPE is large. It does not give a crisp 'use this instead of X' decision rule, but the contextual guidance is strong.

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

Deploy Server