Causal Decision Agent

Overview Schema Source Related Servers Discussions Admin

synth_loo

Read-only

Check synthetic control robustness by sequentially dropping each donor unit and re-estimating the counterfactual, revealing which donors drive the treatment effect.

Instructions

Leave-one-out donor sensitivity for Synthetic Control.

Input Schema

TableJSON Schema

Name	Required	Description	Default
`time`	Yes	Time column.
`unit`	Yes	Unit identifier column.
`alpha`	No	Significance level for z-based p-values.
`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	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

C2.5/5.0

Behavior2/5

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

Annotations already declare readOnlyHint=true, so the tool's safe read-only nature is known. The description adds no behavioral context beyond the name itself—no hints about return structure, side effects, or expectations. It fails to disclose any operational traits that aren't already implicit in the tool name.

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 a single short sentence, making it maximally concise, but it lacks structure and front-loading of key information. It is under-specified for a tool with 13 parameters and complex options, so while it is brief, it doesn't effectively guide usage. The short length is not offset by informative content.

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 complexity (13 parameters, multiple optional features like detail levels, as_handle, penalization), this one-line description is grossly inadequate. It provides no explanation of the tool's role in a workflow, no clarification of the specialized 'detail' parameter or chaining via as_handle, and leaves an agent without sufficient context to invoke it appropriately.

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 each parameter documented, so the schema provides full semantic meaning for all 13 parameters. The description adds no additional parameter-level information, which aligns with the baseline of 3 since the schema carries the burden entirely.

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 states a specific operation ('Leave-one-out donor sensitivity') and a clear target ('Synthetic Control'), which distinguishes it from sibling tools like synth_sensitivity or synth_donor_sensitivity. However, it doesn't explicitly contrast with these siblings, making it only slightly above baseline clarity.

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?

The description provides no guidance on when to use this tool versus alternatives. There is no mention of scenarios, exclusions, or recommended contexts. The absence of any usage direction makes it nearly impossible for an agent to decide between this and related synth sensitivity tools.

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

Deploy Server