Causal Decision Agent

Overview Schema Source Related Servers Discussions Admin

synth_to_latex

Read-only

Convert synthetic-control results into a formatted LaTeX table with confidence intervals, weights, and optional diagnostics for reproducible audit traces.

Instructions

Formatted LaTeX table for synthetic-control results.

Input Schema

TableJSON Schema

Name	Required	Description	Default
`obj`	Yes	Object to render. ``SynthComparison`` and lists trigger the side-by-side multi-method layout.
`label`	No	LaTeX label for cross-referencing. Defaults to ``"tab:synth"`` (single) or ``"tab:synth_compare"`` (multi).
`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
`digits`	No	Number of decimal places.
`caption`	No	Table caption. Defaults to a sensible auto-generated string.
`show_ci`	No	Include the confidence-interval row.
`booktabs`	No	If True, use ``\toprule`` / ``\midrule`` / ``\bottomrule`` (requires ``\usepackage{booktabs}``). Falls back to ``\hline`` if False.
`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`	No	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.
`method_names`	No	Override column labels in comparison mode.
`show_weights`	No	Append a panel listing the top-N donor weights.
`data_sample_n`	No	Optional uniform random subsample size (seed=0, deterministic) — useful on huge panels.
`top_n_weights`	No	How many donors to show per method when ``show_weights=True``.

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

C2.8/5.0

Behavior2/5

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

Annotations already declare readOnlyHint=true, and the description adds no behavioral context beyond that. It does not state whether the tool renders from an existing fitted result, can re-run estimation from data_path, or returns cached handles when as_handle is true. No contradiction, but no added transparency.

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 short, front-loaded, and contains no filler words. However, it is a noun phrase rather than a full statement of action, and a second sentence clarifying what the tool consumes and produces would make it more useful without adding bulk.

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?

For a 15-parameter tool with many sibling exporters, a one-line description is insufficient. It does not clarify that it converts an existing synthetic-control fit or comparison object into LaTeX, does not explain how it relates to synth_to_markdown/synth_to_excel, and does not mention the as_handle or data_path workflows that the schema exposes.

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 description coverage is 100%, so the schema carries the semantic burden for all 15 parameters and the description does not need to repeat them. The description itself adds no parameter-level meaning, which is acceptable at the baseline.

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 the output artifact ('LaTeX table') and the domain ('synthetic-control results'), so an agent can infer this is an export/rendering tool. It lacks an explicit verb like 'render' or 'generate' and does not mention side-by-side or comparison support, so it stops short of being a fully explicit purpose statement.

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?

The description gives no guidance on when to use this tool instead of alternatives. Siblings like synth_to_markdown and synth_to_excel exist but are not referenced, and there is no statement about the conditions that should trigger LaTeX export.

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

Deploy Server