Causal Decision Agent

Overview Schema Source Related Servers Discussions Admin

rdrandinf

Read-only

Run randomization inference to test treatment effects in regression discontinuity designs, with automatic assumption checks for continuity and no sorting.

Instructions

Randomization inference for regression discontinuity designs. Validation: certified parity evidence. Assumptions: Conditional expectations of potential outcomes are continuous at the cutoff; Units cannot precisely manipulate the running variable around the cutoff (no sorting); For fuzzy designs: monotonicity of treatment take-up at the cutoff. Pre-conditions: A continuous running/forcing variable with a known cutoff that (sharply or fuzzily) assigns treatment; Enough observations in a neighbourhood of the cutoff to fit a local polynomial. Failure modes: Density of the running variable jumps at the cutoff (manipulation / sorting) -> Run a McCrary / density test (rdplotdensity); if manipulation is present the design is invalid near the cutoff; Estimate swings with the bandwidth -- results are not robust -> Report a bandwidth-sensitivity curve and use a data-driven MSE-optimal bandwidth. Alternatives: sp.rdrobust, sp.rdrandinf, sp.rdbwselect. Typical minimum N: 500.

Input Schema

TableJSON Schema

Name	Required	Description	Default
`c`	No	RD cutoff value.
`p`	No	Polynomial order for adjustment (0 = unadjusted).
`x`	Yes	Running variable name.
`y`	Yes	Outcome variable name.
`wl`	No	Window left bound offset from cutoff (typically negative). The left edge of the window is ``c + wl``.
`wr`	No	Window right bound offset from cutoff (typically positive). The right edge of the window is ``c + wr``.
`covs`	No	Covariate names to partial out before testing.
`seed`	No	Random seed for reproducibility.
`alpha`	No	Significance level.
`fuzzy`	No	Actual treatment variable for fuzzy RD. The Wald (IV) estimator is computed within the window.
`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 weighting (only 'uniform' currently supported for local randomization).	uniform
`n_perms`	No	Number of permutations for Fisher randomization test.
`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.
`statistic`	No	Test statistic: 'diffmeans', 'ksmirnov', 'ranksum', or 'all'. ``'ttest'`` is accepted as an alias for ``'diffmeans'``, matching rdlocrand, where both names select the same statistic.	diffmeans
`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

A4.1/5.0

Behavior5/5

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

The description goes well beyond the read-only annotation by disclosing key assumptions, failure modes, and follow-up actions such as running a density test and reporting bandwidth sensitivity. It also names alternatives and a typical minimum sample size, giving agents concrete behavioral expectations without contradicting annotations.

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 compact, well organized into labeled sections, and front-loads the core purpose. Every section contributes practical guidance, and the structure makes the content easy to scan.

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

Completeness5/5

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

For a complex RD tool, the description covers validation status, assumptions, pre-conditions, failure modes, alternatives, and minimum data requirements, while the rich input schema and output schema fill in the remaining operational details. An agent has enough context to select and invoke the tool appropriately.

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 baseline is 3 and the schema already documents every parameter. The description adds context around ideas like local polynomial fitting and bandwidth sensitivity, but it does not need to restate parameter semantics beyond what the schema provides.

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 clearly identifies the method ('randomization inference') and target design ('regression discontinuity designs'), so an agent can infer what the tool computes. However, it does not explicitly differentiate this from closely related sibling tools like rdrobust or rdbwselect beyond listing them as alternatives.

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

Usage Guidelines3/5

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

The description provides assumptions, pre-conditions and failure modes, which imply when the tool is applicable, and it lists alternatives. It stops short of explicitly stating 'use this when you need randomization inference near the cutoff' or 'use rdrobust when ...' This is useful context but not crisp routing.

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

Deploy Server