Causal Decision Agent

Overview Schema Source Related Servers Discussions Admin

synth_recommend

Read-only

Recommends the optimal synthetic control method for your dataset using outcome, time, and unit columns. Provides actionable guidance for causal analysis.

Instructions

Quickly recommend the best SCM method for the given data.

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
`outcome`	Yes	Outcome variable column 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://.
`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`	No	Identifier of the treated unit.
`data_sample_n`	No	Optional uniform random subsample size (seed=0, deterministic) — useful on huge panels.
`treatment_time`	No	First treatment period (inclusive).

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

B3.3/5.0

Behavior3/5

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

Annotations declare readOnlyHint=true, so there is no contradiction; the description adds that this is a recommendation rather than an estimation or fitting operation. It does not, however, disclose how the recommendation is produced, what data assumptions apply, or any side effects beyond what the annotations already cover.

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?

A single front-loaded sentence conveys the core purpose with no filler or repetition. Every word is informative and the structure is easily scanned.

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

Completeness3/5

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

The rich schema and output schema carry much of the invocation burden, but the description remains incomplete for a complex 11-parameter tool: it does not define SCM, explain when to prefer this over generic recommend, or outline expected use cases. This is adequate but not complete.

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?

Input schema coverage is 100%, so the schema already documents all 11 parameters thoroughly. The description only alludes to 'the given data' and adds no parameter-level meaning beyond the schema's 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 uses a specific verb ('recommend') and resource ('best SCM method for the given data'), and the synth_ prefix helps distinguish it from generic siblings like recommend. However, 'SCM' is left as an undefined acronym and there is no explicit contrast with related siblings, so it does not fully reach the top level of differentiation.

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

Usage Guidelines2/5

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

No guidance is provided about when to call synth_recommend versus siblings such as synth, recommend, or recommend_benchmark. The word 'Quickly' implies speed but does not state when/when-not to use the tool or what alternatives exist.

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

Deploy Server