Causal Decision Agent

Overview Schema Source Related Servers Discussions Admin

geographic_rd

Read-only

Estimate causal treatment effects in geographic regression discontinuity designs at known cutoffs, with diagnostics for manipulation and bandwidth sensitivity.

Instructions

User-friendly alias for :func:sp.rdms (multi-score RD). Assumptions: Conditional expectations of potential outcomes are continuous at the cutoff; Units cannot precisely manipulate the running variable around the cutoff (no sorting); For fuzzy designs: monotonicity of treatment take-up at the cutoff. Pre-conditions: A continuous running/forcing variable with a known cutoff that (sharply or fuzzily) assigns treatment; Enough observations in a neighbourhood of the cutoff to fit a local polynomial. Failure modes: Density of the running variable jumps at the cutoff (manipulation / sorting) -> Run a McCrary / density test (rdplotdensity); if manipulation is present the design is invalid near the cutoff; Estimate swings with the bandwidth -- results are not robust -> Report a bandwidth-sensitivity curve and use a data-driven MSE-optimal bandwidth. Alternatives: sp.rdrobust, sp.rdrandinf, sp.rdbwselect. Typical minimum N: 500.

Input Schema

TableJSON Schema

Name	Required	Description	Default
`y`	Yes	Outcome variable column name or outcome array.
`x1`	Yes	x1 parameter (str).
`x2`	Yes	x2 parameter (str).
`alpha`	No	Significance level for confidence intervals and tests.
`treat`	No	Treatment indicator or first-treatment-period column.
`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
`cutoff1`	No	cutoff1 parameter (float).
`cutoff2`	No	cutoff2 parameter (float).
`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.
`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

A4.5/5.0

Behavior5/5

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

The description goes well beyond the read-only annotation by disclosing statistical assumptions, failure modes (density jump, bandwidth sensitivity), and remediation steps (rdplotdensity, bandwidth-sensitivity curve, MSE-optimal bandwidth). This gives the agent a realistic model of when results may be invalid and what to do about it.

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?

Although dense, every sentence earns its place: alias identity, assumptions, pre-conditions, failure modes, alternatives, and a typical minimum sample size are each compactly grouped. The most important fact (what this tool is an alias for) is front-loaded.

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 statistical tool with an output schema, the description supplies assumptions, validity checks, failure diagnostics, alternative tools, and a sample-size guideline. This is unusually complete and leaves an agent well-equipped to decide whether and how to call it.

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 all 15 parameters. The description does not add parameter-level semantics beyond the schema, but it does provide domain context about cutoffs, running variables, and fuzzy designs that indirectly helps interpret parameters. 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 names the exact function it aliases ('sp.rdms (multi-score RD)') and labels the operation as a user-friendly alias, so an agent immediately knows what resource and method family this belongs to. It also distinguishes itself from related RD tools by naming rdrobust, rdrandinf, and rdbwselect as alternatives.

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?

Assumptions and pre-conditions make the appropriate invocation context explicit: continuous running variable, known cutoff, sharp/fuzzy assignment, and enough observations. It names alternatives such as sp.rdrobust and sp.rdrandinf, but does not give explicit condition-based selection rules for when to choose each alternative over this tool.

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

Deploy Server