Causal Decision Agent

Overview Schema Source Related Servers Discussions Admin

rd_cate_summary

Read-only

Compare conditional average treatment effect estimates from multiple machine-learning regression discontinuity methods to identify robust causal conclusions.

Instructions

Run multiple ML-RD methods and compare CATE estimates.

Input Schema

TableJSON Schema

Name	Required	Description	Default
`c`	No	RD cutoff.
`h`	No	Bandwidth (shared across methods).
`x`	Yes	Running variable.
`y`	Yes	Outcome variable.
`covs`	No	Covariates for heterogeneity / selection.
`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
`methods`	No	Subset of ``['forest', 'boost', 'lasso']``. Default: all three.
`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

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 the description is consistent with that: running methods and comparing estimates is a non-mutating analysis operation. The description adds the 'multiple methods and comparison' scope but does not disclose behavioral details like computation cost, caching semantics, or randomness; those are covered in parameter descriptions, so no contradiction or major gap.

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

Conciseness5/5

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

A single sentence with no filler, front-loaded with the action verb and object. Every word contributes to stating the tool's purpose, making it highly economical.

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?

With a full output schema and 100% schema coverage, the description does not need to repeat return-value or parameter details. However, given the tool's complexity (14 parameters) and the large sibling set, the one-line description provides no prerequisite context, no example, and no explicit guidance on how this compares to similar CATE or ML-RD tools.

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?

The input schema has 100% parameter description coverage, with rich details for data_path, detail, methods, as_handle, and others. The description itself adds no parameter-level meaning, which is acceptable because the schema already carries the burden.

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 uses specific verbs and resources: 'Run multiple ML-RD methods and compare CATE estimates.' It clearly conveys the core function of the tool. However, it does not differentiate from closely related siblings such as cate_summary, auto_cate, or compare_estimators, and 'ML-RD' may be ambiguous without domain context.

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 on when to use this tool versus alternatives, no exclusions, and no mention of relevant sibling tools. The phrase 'compare CATE estimates' implies a comparison use case, but the agent is not told when this is the right choice among the many overlapping CATE-related siblings.

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

Deploy Server