Causal Decision Agent

Overview Schema Source Related Servers Discussions Admin

kink_unified

Read-only

Run regression discontinuity, kink design, and bunching analyses on the same dataset to estimate behavioral responses at a known threshold.

Instructions

Run RDD + RKD + Bunching on the same data. Assumptions: The counterfactual density would be smooth through the threshold absent the policy; Excess mass at the threshold reflects the behavioural elasticity of interest; No other discontinuity coincides with the threshold. Pre-conditions: A behavioural choice variable (earnings, hours, ...) with a known kink or notch in the budget/choice set; A visible empirical density of the running variable around the threshold. Failure modes: Round-number heaping or a coincident policy contaminates the bunching mass -> Exclude heaping points, widen the excluded region, and test the counterfactual polynomial order. Alternatives: sp.rdrobust, sp.rkd. Typical minimum N: 500.

Input Schema

TableJSON Schema

Name	Required	Description	Default
`y`	Yes	Outcome variable (used by RDD/RKD).
`alpha`	No	Significance level for confidence intervals and tests.
`cutoff`	No	cutoff parameter (float).
`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
`running`	Yes	Running variable (also forms density for Bunching).
`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	Bandwidth used for local smoothing or kernel weighting.
`bin_width`	No	bin_width parameter (Optional[float]).
`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.
`polynomial_order`	No	polynomial_order parameter (int).

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

A4.5/5.0

Behavior5/5

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

Beyond the readOnlyHint annotation, the description discloses statistical assumptions (smooth counterfactual density, excess mass interpretation, no coincident discontinuity), failure modes (heaping, coincident policy), and mitigations. This is substantial behavioral context an agent needs to interpret results and avoid misuse.

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?

The first sentence front-loads the purpose. Assumptions, pre-conditions, failure modes, alternatives, and typical sample size are each succinctly labeled and directly useful. No filler or redundant sentences.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a complex tool with 13 parameters and an existing output schema, the description covers assumptions, preconditions, failure modes, alternatives, and minimum N. Return-value details are unnecessary because the output schema exists, and parameter details are fully in the input schema.

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% description coverage for all 13 parameters, so the baseline is 3. The description does not add parameter-specific details, but it does not need to because the schema already documents every parameter clearly.

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 verb, resource, and scope: 'Run RDD + RKD + Bunching on the same data.' It also names alternatives (sp.rdrobust, sp.rkd), making it easy to distinguish this combined tool from single-method siblings.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

It provides pre-conditions (behavioral choice variable with known kink/notch, visible density), failure modes, and explicitly names alternatives. It does not explicitly say 'use this only when you want all three methods', but the alternatives and preconditions convey the selection logic well.

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

Deploy Server