Causal Decision Agent

Overview Schema Source Related Servers Discussions Admin

rd_boost

Read-only

Estimate heterogeneous treatment effects in regression discontinuity designs using gradient boosting. Handles covariate-based CATE heterogeneity and automatic bandwidth selection.

Instructions

Gradient Boosting for RD -- flexible CATE estimation.

Input Schema

TableJSON Schema

Name	Required	Description	Default
`c`	No	RD cutoff.
`h`	No	Bandwidth (auto-selected if None).
`x`	Yes	Running variable.
`y`	Yes	Outcome variable.
`covs`	No	Covariate names for heterogeneity.
`seed`	No	Random seed.
`alpha`	No	Significance level.
`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
`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://.
`max_depth`	No	Maximum tree depth per round.
`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.
`n_estimators`	No	Number of boosting rounds.
`data_sample_n`	No	Optional uniform random subsample size (seed=0, deterministic) — useful on huge panels.
`learning_rate`	No	Shrinkage factor.

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

B3.2/5.0

Behavior3/5

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

Annotations already declare readOnlyHint=true, so the safety profile is covered. The description adds that it estimates CATE (flexible heterogeneity) rather than just an average effect, which is useful behavioral context. It does not mention bandwidth selection or any other quirks, but with annotations covering the main concern, this is acceptable.

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, efficient sentence that front-loads the core purpose. It avoids redundancy and doesn't waste words. While it could add a bit more context, it is appropriately concise for a tool with a rich schema.

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?

Given the tool's complexity (16 params), the schema and output schema cover most details. The description is minimal, and while it names the method and CATE, it doesn't provide selection guidance among the many RD siblings. This is a noticeable gap, but not critical given the schema richness.

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 have descriptions. The tool description adds nothing about parameters, so the schema carries the full burden. Baseline 3 is appropriate because the description doesn't compensate for any gaps, but there are no gaps.

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 states it performs gradient boosting for RD (regression discontinuity) and estimates CATE (conditional average treatment effects). This distinguishes it from parametric RD estimators like rdrobust. However, it doesn't explicitly spell out 'regression discontinuity,' relying on the name and context, so it's clear but not maximally explicit.

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 is provided on when to use this tool versus alternatives like rd_forest, rd_flex, or rdrobust. The description only states what it does, leaving the agent to infer selection criteria from the name and parameter list.

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

Deploy Server