Causal Decision Agent

Overview Schema Source Related Servers Discussions Admin

synth_report

Read-only

Generate a synthetic control analysis report from panel data to estimate causal impact, including diagnostics, sensitivity checks, and suggested next steps for evidence-backed decisions.

Instructions

Generate a comprehensive Synthetic Control analysis report.

Input Schema

TableJSON Schema

Name	Required	Description	Default
`time`	Yes	Time period column.
`unit`	Yes	Unit identifier column.
`alpha`	No	Significance level for CIs and hypothesis tests.
`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
`method`	No	SCM variant passed to ``synth()``.	classic
`output`	No	Output format: ``'text'``, ``'markdown'``, or ``'latex'``.	text
`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://.
`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.
`sensitivity`	No	Whether to include the sensitivity analysis section.
`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

C2.6/5.0

Behavior2/5

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

The description adds no behavioral detail beyond the readOnlyHint annotation. It does not disclose what 'comprehensive' includes (sections, output length, execution time), whether it performs heavy computation, or what the returned payload structure is. Since annotations already cover safety, the description adds minimal value.

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

Conciseness4/5

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

The description is a single, focused sentence with no fluff. It is concise and front-loaded, but it sacrifices substance for brevity. The structure is acceptable, though it lacks critical context that could be added without bloat.

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

Completeness2/5

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

Given the tool's complexity (15 parameters, 4 required, many sibling tools) and the existence of an output schema, a one-line description is inadequate. The description does not explain what the report provides, how to specify the treatment setup, or how it relates to the synth family. The output schema may define the return shape, but the semantic context is 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?

The input schema documents all 15 parameters with descriptions (100% coverage), so the baseline is 3. The description adds no additional parameter context, such as how treated_unit and treatment_time interact or what the 'detail' enum values mean beyond the schema. It neither hurts nor helps beyond the schema.

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 states a specific verb ('Generate') and resource ('comprehensive Synthetic Control analysis report'), but it is too generic to distinguish from many sibling tools like synth_compare, synth_sensitivity, or synth_report_to_file. It doesn't indicate what the report contains (e.g., point estimates, diagnostics, sensitivity) or how it differs from other synth utilities.

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?

There is no guidance on when to use this tool versus alternatives. No mention of conditions (e.g., 'use this for a full narrative report') or exclusions. The agent is left to infer that this is the primary report generator, but with over 20 synth-related siblings, explicit routing is needed.

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

Deploy Server