Causal Decision Agent

Overview Schema Source Related Servers Discussions Admin

rdplot

Read-only

Create a regression-discontinuity plot with binned scatter and polynomial fits on both sides of a cutoff to visually inspect treatment effects and discontinuity at the threshold.

Instructions

RD plot: binned scatter with polynomial fit on each side of the cutoff.

Input Schema

TableJSON Schema

Name	Required	Description	Default
`c`	No	Cutoff.
`h`	No	Bandwidth to display.
`p`	No	Polynomial order for the fitted curve.
`x`	Yes	Outcome and running variable names.
`y`	Yes	Outcome and running variable names.
`ax`	No	ax parameter (Optional[Any]).
`covs`	No	Covariates to partial out before binning and plotting.
`donut`	No	If > 0, shades the donut region \|x - c\| <= donut.
`nbins`	No	Bins per side. If None, uses data-driven selection via binselect.
`title`	No	title parameter (Optional[str]).
`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
`kernel`	No	Kernel for the fitted curve.	triangular
`figsize`	No	figsize parameter (Tuple[float, float]).
`hide_ci`	No	If True, suppress CI bands entirely.
`scatter`	No	Show binned scatter points.
`show_bw`	No	If True, shades the bandwidth window.
`weights`	No	Column name for observation weights in polynomial fitting.
`x_label`	No	x_label parameter (Optional[str]).
`y_label`	No	y_label parameter (Optional[str]).
`ci_level`	No	Confidence level for pointwise CI bands.
`shade_ci`	No	Show confidence interval bands around the polynomial fit.
`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.
`binselect`	No	Bin selection method (when nbins=None): - 'es' : IMSE-optimal evenly spaced - 'espr' : IMSE-optimal evenly spaced (mimicking variance) - 'qs' : IMSE-optimal quantile-spaced - 'qspr' : IMSE-optimal quantile-spaced (mimicking variance) - 'esmv' : IMSE-optimal evenly spaced with variance mimicking (default) - 'qsmv' : IMSE-optimal quantile-spaced with variance mimicking	esmv
`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.
`data_sample_n`	No	Optional uniform random subsample size (seed=0, deterministic) — useful on huge panels.

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

A3.6/5.0

Behavior3/5

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

Annotations already declare readOnlyHint=true and openWorldHint=false, so the safety profile is covered. The description adds a useful behavioral detail: the polynomial is fit separately on each side of the cutoff. It does not discuss output behavior such as whether a figure object is returned, but the presence of an output schema lowers the burden.

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?

The description is a single tight sentence with no filler. It front-loads the core purpose ('RD plot') and immediately adds the distinguishing details ('binned scatter,' 'polynomial fit,' 'each side of the cutoff'). Every word earns its place.

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

Completeness4/5

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

Given the extremely detailed input schema and an output schema, the description does not need to enumerate parameters or return fields. It provides sufficient high-level context for an agent to understand what the tool does. It is slightly less complete in not connecting this tool to siblings or the broader RD workflow, but this is not critical for a plotting tool with rich structured metadata.

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 input schema fully documents all 27 parameters, including enums for binselect and depth for detail. The description itself adds no parameter-level meaning beyond the phrase 'cutoff,' which maps to the c parameter. Baseline 3 is appropriate because the schema carries the explanatory load.

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

Purpose5/5

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

The description uses a specific verb ('plot') and resource ('RD'), and specifies the exact visualization content: 'binned scatter with polynomial fit on each side of the cutoff.' This clearly distinguishes it from estimation-focused siblings like rdrobust and density-focused rdplotdensity. A single sentence fully conveys what the tool produces.

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 explicit guidance on when to use this tool versus alternatives such as rdplotdensity, rdrobust, or rdsummary. There is no 'use this when...' statement, no exclusions, and no mention of the RDD plotting workflow this belongs to. Usage must be inferred entirely from the tool name and the word 'plot.'

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

Deploy Server