Causal Decision Agent

Overview Schema Source Related Servers Discussions Admin

rdbwsensitivity

Read-only

Run bandwidth sensitivity analysis for regression discontinuity estimates to check how results vary across bandwidth choices, supporting robust causal conclusions.

Instructions

Bandwidth sensitivity analysis for RD estimates.

Input Schema

TableJSON Schema

Name	Required	Description	Default
`c`	No	Cutoff.
`p`	No	Polynomial order.
`x`	Yes	Outcome and running variable names.
`y`	Yes	Outcome and running variable names.
`ax`	No	ax parameter (Optional[Any]).
`alpha`	No	Significance level for confidence intervals and tests.
`fuzzy`	No	Treatment variable for fuzzy RD.
`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 function used for weighting or smoothing.	triangular
`n_grid`	No	Number of grid points if bw_grid is None.
`bw_grid`	No	Explicit bandwidth values to evaluate. If None, auto-generates a grid as multiples of the MSE-optimal bandwidth.
`figsize`	No	figsize parameter (Tuple[float, float]).
`bw_range`	No	Range of multipliers for the optimal bandwidth.
`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

C2.7/5.0

Behavior2/5

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

Annotations declare readOnlyHint=true, which covers the safety profile. However, the description adds no extra behavioral context beyond that. It does not mention any side effects, caching behavior (as_handle), or specifics about what the analysis entails. Since annotations already cover the read-only nature, the lack of additional context is acceptable but not enriching.

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

Conciseness3/5

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

The description is extremely concise with no wasted words, which is efficient. However, it is a single sentence with no structure, and it is so minimal that it borders on under-specification rather than genuine conciseness. It lacks front-loaded key details that would help an agent quickly understand its use.

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 18 parameters and many optional features, yet the description provides almost no context. It does not explain what the analysis produces, how it relates to other RD tools, or when it should be invoked. The description is inadequate for an agent to make an informed decision about using this tool, especially given the large sibling set.

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 every parameter has a description in the input schema. The tool description adds no additional meaning about parameters. Per the rubric, with high schema coverage, a baseline of 3 is appropriate, and the description does not elevate it.

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 states a clear purpose: bandwidth sensitivity analysis for RD estimates. It identifies the specific verb (analysis) and resource (bandwidth sensitivity), distinguishing it from generic analysis tools. However, it does not explicitly differentiate from closely related siblings like rdsensitivity or rdrobust, which limits its clarity.

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 provides no guidance on when to use this tool versus alternatives. There are no conditions, exclusions, or references to sibling tools that might be more appropriate for different scenarios. The single sentence gives no context for selection.

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

Deploy Server