Causal Decision Agent

Overview Schema Source Related Servers Discussions Admin

rd_robustness_table

Read-only

Run robustness checks for regression discontinuity estimates by sweeping across kernel, bandwidth selection, polynomial order, and donut specifications, and return a comparison table of results.

Instructions

Sweep over (kernel, bwselect, polynomial, donut) and return a

Input Schema

TableJSON Schema

Name	Required	Description	Default
`c`	No	c parameter (float).
`x`	Yes	Primary running variable, regressor, or feature input for this estimator.
`y`	Yes	Outcome variable column name or outcome array.
`covs`	No	covs parameter (Optional[List[str]]).
`alpha`	No	Significance level for confidence intervals and tests.
`fuzzy`	No	fuzzy 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
`donuts`	No	Specification grid.
`cluster`	No	Cluster identifier column for clustered standard errors.
`kernels`	No	Specification grid.
`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.
`bwselects`	No	Specification grid.
`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.
`polynomials`	No	Specification grid.
`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

C2.4/5.0

Behavior2/5

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

The readOnlyHint and openWorldHint annotations cover the safety profile, so the description does not need to restate that. But the description adds little behavioral context: it says 'sweep' and then stops, without explaining that this runs multiple RD fits, what the returned object contains, or how it relates to a single rdrobust call. No contradiction with annotations exists.

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 very short, but it is under-specified rather than concise: the final clause is cut off ('return a'). A complete sentence naming the output and purpose would be more efficient for an agent than a fragment that forces inference from the tool name.

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?

Given 17 parameters, 3 required inputs, and a large family of RD-related sibling tools, the description needs at least a complete statement of what is returned and when this robustness sweep is appropriate. The output schema covers return structure, but the description fails to give the operational context needed to select and invoke the tool confidently.

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. The description adds mild value by naming the four swept dimensions (kernel, bwselect, polynomial, donut), but it does not explain their meaning or how they interact beyond what the schema's 'Specification grid' entries already convey.

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

Purpose3/5

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

The description names a concrete action — sweeping over kernel, bwselect, polynomial, and donut — so it is not a pure tautology. However, the sentence is truncated after 'return a', leaving the output object unspecified. It also does not differentiate this tool from nearby RD siblings such as rdrobust, rdsummary, or rdbwselect.

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?

There is no guidance about when to use this tool versus alternatives, no when-not-to-use note, and no mention of prerequisites or typical workflow placement. The only implied usage is that the tool varies specification dimensions, but that is not explicit enough to route an agent reliably.

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

Deploy Server