Causal Decision Agent

Overview Schema Source Related Servers Discussions Admin

conformal_synth

Read-only

Estimate treatment effects using synthetic control with conformal inference, yielding confidence intervals and assumption checks to support causal decisions.

Instructions

Conformal inference for 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.
`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://.
`grid_size`	No	Number of points in the hypothesis grid for CI inversion.
`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.
`grid_range`	No	(min, max) of the hypothesis grid. If None, auto-determined from pre-treatment residual scale.
`scm_method`	No	Which SCM variant to use for weight estimation. Currently supports 'classic' (constrained) and 'ridge'.	classic
`data_columns`	No	Optional column projection. Parquet/Feather/Stata loaders honour this for fast partial reads.
`penalization`	No	Ridge penalty (used when scm_method='ridge').
`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?

The description goes well beyond the sparse readOnlyHint annotation by disclosing identifying assumptions (SUTVA, no anticipation), preconditions, and failure modes such as large pre-treatment RMSPE and non-extreme placebo estimates. It tells the agent what can go wrong and what actions to take. No contradiction with annotations is present.

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 compact for the amount of content it carries, with labeled sections for Assumptions, Pre-conditions, Failure modes, Alternatives, and typical N. It is front-loaded with the purpose, and each segment adds decision-relevant information without filler.

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 16-parameter, method-heavy tool with an output schema, this description provides the assumptions, prerequisites, failure handling, alternatives, and sample-size rule of thumb an agent needs before calling. The schema and output schema cover the mechanical parameters, so nothing essential appears missing.

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 descriptions cover 100% of parameters, so the description is not required to repeat parameter details. It does conceptually contextualize donor weights, pre-period length, treated unit, and treatment time, but it adds no direct syntax or format guidance beyond the schema. 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 opens with the specific method ('Conformal inference for synthetic control') and then details assumptions, preconditions, failure modes, and alternatives. It clearly identifies what the tool computes and distinguishes it from sibling SCM tools, though it uses a noun phrase rather than an explicit verb such as 'estimates'.

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 spell out the data requirements (treated unit plus donor pool, panel, long pre-period), and failure modes advise when the estimate is unreliable and mention bias-corrected alternatives sd and augsynth. Alternative tools are listed, though the mapping of when to prefer each alternative over conformal_synth is not fully specified.

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

Deploy Server