Causal Decision Agent

Overview Schema Source Related Servers Discussions Admin

rdrobust

Read-only

Estimate sharp or fuzzy regression-discontinuity effects with robust bias-corrected confidence intervals, including IV-style fuzzy RD using a treatment column.

Instructions

Sharp or fuzzy regression-discontinuity with robust bias-corrected CIs (Calonico-Cattaneo-Titiunik 2014). Use fuzzy= for IV-style fuzzy RD. Validation: certified evidence with scoped limitations. Known limitations: observation-level weights are not yet supported -- passing a weight column raises NotImplementedError; R-parity certification applies to bwselect='cct' or manually matched h/b bandwidths; the dependency-light default bwselect='mserd' uses StatsPAI's calibrated selector and can differ from rdrobust::rdrobust defaults.

Input Schema

TableJSON Schema

Name	Required	Description	Default
`c`	No	Cutoff value.
`x`	Yes	Running variable column.
`y`	Yes
`fuzzy`	No	Treatment column for fuzzy RD (optional).
`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		triangular
`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.
`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

Behavior5/5

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

The description discloses several important behavioral traits beyond the readOnlyHint annotation: observation-level weights are unsupported and raise NotImplementedError, R-parity certification only applies to specific bandwidth selectors, and the default bwselect='mserd' differs from the canonical R package. This is valuable, specific context that would prevent misuse.

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 two sentences plus a dense limitations sentence, front-loaded with the core method. It is compact but the limitations paragraph packs multiple issues into one run-on sentence, making it less scannable. Still, it earns its place.

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

Completeness3/5

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

For a complex tool with an output schema present, the description covers the method, limitations, and validation, but omits any guidance on tool selection (covered by usage_guidelines) and references parameters not in the schema. The output schema handles return values, so that absence is fine, but the misleading parameter references and lack of selection context make it incomplete.

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 already documents 82% of parameters. The description augments the fuzzy= parameter by calling it 'IV-style fuzzy RD,' and explains the default bandwidth selector behavior. However, it also references bwselect, h, and b, which are not present in the input schema, potentially misleading an agent into passing unsupported parameters. Given the high schema coverage, the description's net addition is modest and partly confusing.

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 tool as implementing sharp or fuzzy regression-discontinuity with robust bias-corrected CIs, citing the methodology. It also notes the fuzzy= parameter for IV-style fuzzy RD, but does not explicitly differentiate it from sibling RD tools such as rdd or rdplot.

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?

No explicit guidance on when to choose this tool over alternatives. The description provides internal usage notes (e.g., 'Use fuzzy=') but does not mention any exclusion criteria or alternative tool names. It states limitations, but that does not help an agent select among sibling tools.

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

Deploy Server