Causal Decision Agent

Overview Schema Source Related Servers Discussions Admin

augsynth

Read-only

Correct poor pre-treatment fit in synthetic control with ridge bias correction to estimate treatment effects from panel data.

Instructions

Augmented Synthetic Control with ridge bias correction (Ben-Michael et al. 2021). Validation: certified parity evidence. Do NOT use when: pre-treatment fit from plain sp.synth is already good -- the ridge augmentation mainly buys bias correction for poor fit and adds a tuning parameter to justify; many treated units -- use sp.gsynth or sp.sdid. 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...

Input Schema

TableJSON Schema

Name	Required	Description	Default
`time`	Yes	Time period column.
`unit`	Yes	Unit identifier 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
`backend`	No	Computation backend: native or augsynth/R bridge backend	native
`outcome`	Yes	Outcome variable column name or outcome array.
`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.
`treated_unit`	Yes	treated_unit parameter (str).
`data_sample_n`	No	Optional uniform random subsample size (seed=0, deterministic) — useful on huge panels.
`treatment_time`	Yes	treatment_time parameter (int).

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

A4/5.0

Behavior4/5

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

Beyond the readOnlyHint annotation, the description discloses modeling assumptions (SUTVA, no anticipation), preconditions, and failure modes such as large pre-treatment RMSPE and non-extreme placebo estimates. It does not contradict the annotations. The truncated final failure-mode sentence and the unexplained 'certified parity evidence' line prevent a 5.

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

Conciseness3/5

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

The description is organized with labeled sections and is mostly front-loaded, but it runs long and includes unhelpful or redundant content ('Validation: certified parity evidence', and suggesting augsynth within augsynth's own failure mode). It is also cut off mid-sentence at 'the effect...'.

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, the description covers assumptions, preconditions, failure modes, and alternatives; the output schema relieves it from describing return values. Completeness is slightly undercut by the truncated final sentence and the opaque validation line, but the core information an agent needs to call it correctly is present.

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 the baseline applies; most parameter descriptions are adequate and data_path is detailed. The tool description adds context about data shape (donor pool, pre-treatment window) but does not deepen the meaning of specific params like treated_unit or treatment_time beyond their schema descriptions.

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 estimator ('Augmented Synthetic Control with ridge bias correction') with a citation, and contrasts it with plain synth and other panel estimators, so an agent can identify what the tool does. It lacks a direct action verb like 'estimate' or 'fit', and the 'Validation: certified parity evidence' line does not clarify purpose.

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 explicitly gives negative usage conditions ('Do NOT use when: pre-treatment fit ... is already good', 'many treated units') and names alternatives (sp.gsynth, sp.sdid). It also states assumptions and pre-conditions, making it clear when the tool is appropriate.

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

Deploy Server