Causal Decision Agent

Overview Schema Source Related Servers Discussions Admin

rd_external_validity

Read-only

Diagnose whether regression discontinuity estimates generalize beyond the cutoff by testing continuity, manipulation, and bandwidth sensitivity. Identifies threats to external validity and suggests next steps.

Instructions

Diagnostic assessment of RD external validity. 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
`c`	No	RD cutoff value.
`x`	Yes	Running variable name.
`y`	Yes	Outcome variable name.
`covs`	No	Covariate names for overlap and CI testing.
`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://.
`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.
`target_x_range`	No	Running variable range ``(x_low, x_high)`` defining the target population. Defaults to the full data range.

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

A4.1/5.0

Behavior4/5

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

Annotations declare readOnlyHint=true and openWorldHint=false, so the description doesn't need to restate that this is a read-only diagnostic. The description adds valuable behavioral context: it lists the assumptions being tested (continuity, no sorting, monotonicity for fuzzy designs), pre-conditions, and failure modes. It also explains what happens when assumptions fail (design invalid near cutoff, results not robust) and what actions to take. This goes beyond the annotations by disclosing the diagnostic logic and consequences.

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 dense but well-organized: assumptions, pre-conditions, failure modes, alternatives, and minimum N are clearly labeled. It front-loads the core purpose and then provides actionable guidance. It's longer than ideal but every section earns its place by helping an agent decide when and how to use the tool. The structure with colons and arrows makes it scannable.

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

Completeness4/5

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

Given the tool's complexity (12 params, output schema present, many RD siblings), the description covers the key decision-relevant context: assumptions, pre-conditions, failure modes, and alternatives. The output schema exists, so return values don't need to be described. The description could be more complete by explaining what 'external validity' means in this RD context and how the diagnostic result is reported, but the essential information for calling the tool correctly is present.

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 12 parameters. The description adds context about the running variable and cutoff (pre-conditions) but doesn't add parameter-specific semantics beyond what the schema provides. The description's mention of 'local polynomial' and 'MSE-optimal bandwidth' hints at the estimation approach but doesn't map to specific parameters like c, x, y, or covs. Baseline 3 is appropriate given full schema coverage.

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 identifies this as a diagnostic assessment of RD external validity, with a specific verb ('Diagnostic assessment') and resource ('RD external validity'). It distinguishes itself from sibling tools like rdrobust, rdrandinf, and rdbwselect by naming them as alternatives. However, it doesn't explicitly state what the tool returns or how it differs from other RD diagnostic tools like rdplotdensity or rddensity, which are mentioned as failure-mode responses rather than alternatives.

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

Usage Guidelines5/5

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

The description provides explicit pre-conditions (continuous running variable, known cutoff, enough observations), failure modes with specific remedies (density jump -> run McCrary/density test; bandwidth sensitivity -> report bandwidth-sensitivity curve and use MSE-optimal bandwidth), and names alternatives (sp.rdrobust, sp.rdrandinf, sp.rdbwselect). It also gives a typical minimum N of 500, which helps an agent decide when this tool is appropriate.

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

Deploy Server