Causal Decision Agent

Overview Schema Source Related Servers Discussions Admin

synth_rmspe_filter

Read-only

Filter synthetic control results by pre-treatment RMSPE multiples to compute robustness p-values (Abadie et al. 2010) for causal inference decisions.

Instructions

Pre-RMSPE-filtered p-value robustness (Abadie et al. 2010).

Input Schema

TableJSON Schema

Name	Required	Description	Default
`time`	Yes	Time 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
`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.
`thresholds`	No	Multiples of treated-unit pre-RMSPE used as cut-offs. Default ``[1, 2, 5, 10, 20, np.inf]``.
`data_columns`	No	Optional column projection. Parquet/Feather/Stata loaders honour this for fast partial reads.
`penalization`	No	Ridge penalty.
`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

C2.1/5.0

Behavior2/5

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

Annotations already declare readOnlyHint=true and openWorldHint=false, providing the safety profile. The description adds only a vague method label ('Pre-RMSPE-filtered...') and does not disclose what the tool actually returns, whether it uses thresholds, or how it behaves when as_handle is true. There is no contradiction, but also no added behavioral context.

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 extremely short, which could be considered concise, but it is under-specified rather than efficiently informative. The single sentence does not meaningfully explain the tool's function or context, so it does not earn its place as the primary descriptive text.

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?

Given the tool's complexity (13 parameters, 6 required, many synth-related siblings) and the fact that the output schema exists but the description does not explain the tool's purpose or invocation context, the description is severely incomplete. An agent would have to rely entirely on schema field names and the tool name to guess behavior.

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?

The input schema has 100% parameter description coverage, so the baseline is 3. The tool description itself provides no parameter semantics, but the schema fully documents all 13 parameters, including thresholds, detail, and as_handle. The description neither adds nor detracts from the schema's clarity.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose3/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description 'Pre-RMSPE-filtered p-value robustness (Abadie et al. 2010)' conveys a general methodological idea but lacks a clear verb and resource. It does not explicitly state that the tool computes robustness p-values after filtering by pre-treatment RMSPE, nor does it distinguish it from siblings like synth_sensitivity, robust_synth, or synth_time_placebo.

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 usage guidance is provided. The description gives no indication of when to use this tool versus alternatives, no prerequisites, and no exclusion criteria. Given the large number of synth-related siblings, an agent receives no directional help.

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

Deploy Server