Causal Decision Agent

Overview Schema Source Related Servers Discussions Admin

bunching

Read-only

Estimate excess mass at a policy threshold to quantify behavioral response to kinks or notches. Provides validated evidence with diagnostics for contaminated bunching.

Instructions

Estimate bunching at a policy threshold. Validation: validated evidence tier (known-truth, reference, external-parity, or Monte Carlo artifact). 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
`dt`	No	Change in marginal tax rate at the kink (for elasticity). E.g., 0.10 for a 10pp increase.
`alpha`	No	Significance level.
`design`	No	'kink' or 'notch'.	kink
`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
`n_bins`	No	Number of bins on each side of the threshold.
`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.
`bin_width`	No	Width of bins. If None, computed from data range / n_bins.
`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.
`threshold`	Yes	Policy threshold (kink/notch point).
`poly_order`	No	Order of the counterfactual polynomial.
`n_bootstrap`	No	Bootstrap iterations for standard errors.
`running_var`	Yes	Name of the running variable (e.g., income).
`bunch_region`	No	(lower, upper) bounds of the bunching region. If None, uses [threshold - 2bin_width, threshold + 2bin_width].
`data_columns`	No	Optional column projection. Parquet/Feather/Stata loaders honour this for fast partial reads.
`random_state`	No	Random seed or RandomState for reproducible stochastic steps.
`data_sample_n`	No	Optional uniform random subsample size (seed=0, deterministic) — useful on huge panels.
`exclude_region`	No	Same as bunch_region unless otherwise specified.

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

A4.3/5.0

Behavior4/5

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

Annotations declare readOnlyHint=true, and the description adds significant behavioral context: validation tier, key assumptions about the counterfactual density and excess mass, pre-conditions, and failure modes with remediation steps. This goes well beyond what annotations alone provide and does not contradict them.

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 description is well-structured with labeled sections (Validation, Assumptions, Pre-conditions, Failure modes, Alternatives, Typical minimum N). Every sentence contributes new information; there is no padding. It is appropriately sized for a complex econometric tool with 18 parameters.

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?

The description covers validation evidence, assumptions, pre-conditions, failure modes with concrete remedies, alternatives, and sample size guidance. An output schema exists, so return values need not be re-described. An agent has what it needs to decide whether to call this tool and how to interpret potential issues.

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 the schema already documents every parameter. The description does not add parameter-level detail beyond the schema, but it does provide general context (e.g., typical N, failure modes). Since the schema carries the burden, per calibration guidelines the baseline of 3 applies.

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 opens with a clear, specific verb and resource: 'Estimate bunching at a policy threshold.' It also names alternatives (sp.rdrobust, sp.rkd), which distinguishes this tool from related siblings without opening their schemas. The scope is unambiguous.

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?

Pre-conditions and typical minimum N give concrete context for when the tool is appropriate. Alternatives are named, but the description does not explicitly state the deciding factors for choosing this tool over sp.rdrobust or sp.rkd. It implies use when the pre-conditions hold but stops short of 'use X if Y, otherwise Z.'

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

Deploy Server