rd_multi_score

Read-only

Estimates causal effects when treatment requires all running variables to exceed their cutoffs, using multi-score regression discontinuity. Delivers point estimates, diagnostics, and recommended next actions.

Instructions

Multi-score RDD: treatment if all running variables exceed cutoffs.

Input Schema

TableJSON Schema

Name	Required	Description	Default
`y`	Yes	Outcome.
`alpha`	No	Significance level for confidence intervals and tests.
`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
`cutoffs`	Yes	One cutoff per running variable (same length).
`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.
`bandwidth`	No	Defaults to median IQR across running vars.
`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.
`running_vars`	Yes	Multiple running variables.
`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

B3.3/5.0

Behavior3/5

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

Annotations already declare readOnlyHint=true and openWorldHint=false, covering the safety profile. The description adds the treatment assignment rule but says nothing about output behavior, side effects, or computational characteristics. Since annotations cover the main behavioral risk, this is adequate but not enriched.

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 a single sentence with no wasted words. It front-loads the method name and the critical condition. However, given the tool's complexity (12 parameters, statistical method), the extreme brevity might be too terse, but there is no redundancy or fluff.

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?

For a complex econometric tool, the one-line description is insufficient. It does not explain the typical use case, provide examples, or mention any caveats about data requirements or interpretation. The output schema covers return structure, but the description leaves the agent guessing about when to invoke this tool and what to expect beyond the raw method name.

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 12 parameters are documented in the schema. The description adds the semantic link between cutoffs and running_vars ('treatment if all running variables exceed cutoffs'), which is useful context but does not detail individual parameter formats or defaults beyond the schema. Baseline 3 is appropriate.

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

Purpose5/5

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

The description states a specific method (multi-score RDD) and the key condition ('treatment if all running variables exceed cutoffs'). This clearly distinguishes it from siblings like multi_cutoff_rd (different cutoff handling) and rd_multi_extrapolate (extrapolation focus). The verb 'multi-score' and resource 'RDD' are precise.

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 guidance on when to use this tool vs. alternatives. With dozens of RDD-related siblings (rdrobust, rddensity, rdplot, etc.), the agent gets no hint about what distinguishes multi-score RDD from other designs or when it is appropriate. No exclusions or comparisons are mentioned.

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

Deploy Server

Causal Decision Agent