Causal Decision Agent

Overview Schema Source Related Servers Discussions Admin

synth_time_placebo

Read-only

Run a time-placebo backdating test to check whether an estimated synthetic control effect is specific to the real treatment time or appears under placebo pre-treatment periods.

Instructions

Time-placebo ("backdating") test for Synthetic Control.

Input Schema

TableJSON Schema

Name	Required	Description	Default
`time`	Yes	Time 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.
`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.
`penalization`	No	Ridge penalty forwarded to SCM.
`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	Real first treatment period.
`n_placebo_times`	No	Max number of placebo treatment times to try. Default is all feasible pre-treatment times (leaving >= 2 pre-periods for each placebo fit).

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

C2.4/5.0

Behavior2/5

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

Annotations already indicate readOnlyHint=true, so the description doesn't need to restate that. However, it adds no behavioral detail about what the test does operationally—does it run many placebo fits? Does it produce a p-value or distribution? This absence means the description contributes nothing beyond the name.

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

Conciseness2/5

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

The description is terse with no filler, but it is a single noun phrase rather than a structured explanation. For a tool with 14 parameters and complex behavior, this is under-specified rather than appropriately sized, so it does not earn a higher score.

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

Completeness1/5

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

With 14 parameters, 6 required, and dozens of synth and placebo-related siblings, a one-line fragment is entirely inadequate. The description does not explain what a time-placebo test is, how to interpret its results, or when to use it, forcing the agent to rely fully on the schema and its own prior knowledge.

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%, with all 14 parameters clearly described in the input schema. The description itself adds no parameter context, but because the schema carries the full burden, a baseline score of 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 names a specific type of test (time-placebo/backdating) for a specific method (Synthetic Control), which distinguishes it from other synth-related tools like synth_power or synth_loo. However, it is a noun phrase rather than a full sentence with an explicit verb, so it leaves some ambiguity about what the test actually computes.

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

Usage Guidelines1/5

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

No guidance is provided on when to use this tool versus the many alternatives in the sibling list, such as synth_donor_sensitivity, synth_loo, or synthdid_placebo. The agent must infer the tool's role solely from its name, which is insufficient for correct selection.

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

Deploy Server