Causal Decision Agent

Overview Schema Source Related Servers Discussions Admin

staggered_synth

Read-only

Estimates causal effects in staggered adoption designs by using a synthetic control of untreated donors to reproduce the treated unit's pre-treatment path.

Instructions

Staggered Adoption 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
`method`	No	* ``'separate'`` -- fit a separate SCM for each treated unit. * ``'pooled'`` -- partially pool weights across cohorts with the same adoption time.	separate
`outcome`	Yes	Outcome variable name.
`placebo`	No	Run placebo inference.
`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.
`treatment`	Yes	Binary treatment indicator (0/1). Units transition from 0 to 1 at their respective adoption times.
`data_columns`	No	Optional column projection. Parquet/Feather/Stata loaders honour this for fast partial reads.
`penalization`	No	Ridge penalty on donor weights.
`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

A3.7/5.0

Behavior4/5

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

Beyond the readOnlyHint annotation, the description details statistical assumptions (SUTVA, no anticipation, convex combination), failure modes, and typical minimum N. It also suggests remedies for common problems, giving agents a clear picture of what can go wrong and how to interpret results.

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 compact yet information-dense, organized by assumptions, pre-conditions, failure modes, alternatives, and minimum N. Each section earns its place; the structure is logical and easy to scan, though not broken into explicit headings.

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?

For a complex estimator with an output schema, the description covers assumptions, preconditions, failure modes, and alternatives, which is largely sufficient. It does not describe return values, but the output schema covers that. It could mention when the tool is inappropriate relative to its alternates, but overall it is complete.

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 coverage is 100%, so all parameters are documented individually. The description adds general context about data requirements (e.g., outcome observed every period) but does not add parameter-specific semantics beyond what the schema already provides.

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 names a specific method ('Staggered Adoption Synthetic Control') and lists alternatives, which distinguishes it from siblings. However, the primary purpose (estimating causal effects in staggered adoption settings) is implied via assumptions and failure modes rather than explicitly stated with a verb like 'estimates'.

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

Usage Guidelines3/5

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

The description provides pre-conditions (panel structure, donor pool, no missing outcomes) and failure modes (high RMSPE, non-extreme placebo), which implicitly indicate when to use the tool. It lists alternatives but does not explicitly state when to choose this tool over them, nor does it give exclusion criteria.

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

Deploy Server