Causal Decision Agent

Overview Schema Source Related Servers Discussions Admin

rdwinselect

Read-only

Selects the optimal window width for local randomization regression discontinuity by testing covariate balance across candidate windows, returning certified parity evidence to validate the chosen bandwidth.

Instructions

Data-driven window selection for local randomization RD. Validation: certified parity evidence.

Input Schema

TableJSON Schema

Name	Required	Description	Default
`c`	No	RD cutoff value.
`p`	No	Polynomial order for adjustment.
`x`	Yes	Running variable name.
`covs`	No	Covariate names to test balance for. If None, uses quantiles of the running variable as pseudo-covariates.
`seed`	No	Random seed.
`wmin`	No	Minimum half-window width. Defaults to the smallest gap between adjacent observations near the cutoff.
`alpha`	No	Significance level for balance (lenient by default to be conservative about window selection).
`wstep`	No	Window increment. Defaults to ``(max_range - wmin) / nwindows``.
`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
`nwindows`	No	Number of windows to evaluate.
`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 for balance testing.	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

B3.1/5.0

Behavior3/5

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

Annotations already provide readOnlyHint=true and openWorldHint=false, covering the safety profile. The description adds that the tool performs validation and reports 'certified parity evidence,' but this phrase is unexplained and no other behavioral details are disclosed. There is no contradiction with annotations.

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 short and front-loaded with the main purpose, but the second sentence is cryptic and introduces jargon ('certified parity evidence') without explanation. It is concise but not every sentence clearly 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?

The schema and output schema carry much of the burden for a 16-parameter tool, and the annotations establish read-only behavior. However, the description is minimal: it lacks guidance on how this relates to sibling RD tools like rdbwselect and does not clarify what 'certified parity evidence' means. It is adequate but has clear gaps.

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 all 16 parameters are documented in the input schema itself. The description adds no additional parameter-level meaning, so the baseline score of 3 is appropriate.

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 resource and action: data-driven window selection for local randomization RD. It names a specific RD subfield, which helps an agent understand the tool's purpose, though it does not explicitly distinguish it from sibling tools like rdbwselect or rdms. The phrase 'Validation: certified parity evidence' adds domain flavor but is opaque.

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. It does not mention rdbwselect, rdms, or any other sibling, and it gives no conditions or exclusions. Usage must be inferred entirely from the tool name and the first clause.

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

Deploy Server