Causal Decision Agent

Overview Schema Source Related Servers Discussions Admin

rd2d_plot

Read-only

Visualize two-dimensional regression-discontinuity boundaries to assess treatment effects around a cut-off. Use scatter, heatmap, or boundary-effect plots to compare outcomes across treated and untreated groups.

Instructions

2D boundary RD visualization.

Input Schema

TableJSON Schema

Name	Required	Description	Default
`y`	Yes	Outcome variable name.
`ax`	No	Pre-existing axes to draw on.
`x1`	Yes	Running variable names.
`x2`	Yes	Running variable names.
`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
`result`	No	Result from ``rd2d()``, used for bandwidth and effect info.
`figsize`	No	Figure size.
`boundary`	No	Boundary function f(x1) -> x2. None implies x1 = 0.
`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://.
`plot_type`	No	``'scatter'``: 2D scatter of (x1, x2) colored by treatment status, with boundary curve and optional bandwidth region. ``'heatmap'``: outcome values displayed as a heatmap with boundary overlay. ``'boundary_effects'``: treatment effect estimates along the boundary (requires ``result`` with multiple eval points).	scatter
`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.
`treatment`	Yes	Binary treatment indicator.
`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

D1.9/5.0

Behavior2/5

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

Annotations declare readOnlyHint=true and openWorldHint=false, so the description does not contradict them. However, the description adds nothing beyond what the annotations already convey. It does not disclose return format, side effects, or any behavioral nuances beyond being a read-only visualization. With annotations present, the bar is lower, but the description still fails to add contextual value.

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

Conciseness2/5

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

The description is extremely short, which is concise, but it is under-specified rather than appropriately sized. A single phrase without a verb or context does not earn its place; it fails to convey the tool's purpose or any actionable information. It is not front-loaded with useful content—it contains no useful content beyond a vague label.

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?

This is a complex tool with 15 parameters, 5 required, and multiple plot types defined in the schema. The description gives no overview, no guidance on which plot_type to choose, no mention of required data columns, and no context on how the tool fits into an RD analysis workflow. It is grossly inadequate for an agent to correctly select and invoke this tool.

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%, meaning every parameter has a description in the input schema. The tool description itself provides no parameter information. Per the rubric, baseline 3 applies when schema covers parameters fully; the description does not need to repeat them, so a 3 is appropriate.

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

Purpose2/5

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

The description '2D boundary RD visualization' is a noun phrase rather than a clear action statement. It identifies a topic (2D boundary RD) but does not specify what the tool does with it—whether it plots a scatter, heatmap, or boundary effects. It barely distinguishes itself from sibling plotting tools like rdplot or rd2d_bw, which also relate to regression discontinuity visualization.

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?

There is no guidance on when to use this tool instead of alternatives. It does not mention prerequisites, typical use cases, or exclusions. An agent has no indication of how this differs from rdplot, rd2d, or other plotting tools in the sibling list.

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

Deploy Server