StatsPAI

pipeline_rd

Read-only

Runs an end-to-end regression discontinuity analysis and returns effect estimates, an RD plot image, McCrary density test, bandwidth sensitivity, and a markdown report with a result handle.

Instructions

End-to-end RD workflow: rdrobust -> rdplot (PNG image) -> rddensity (McCrary) -> rdsensitivity (bandwidth). Returns one markdown report + result_id + an image content block.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "x": "<x>",
      "y": "<y>"
    },
    "name": "pipeline_rd"
  }
}

Input Schema

Name	Required	Description	Default
`c`	No	Cutoff value.
`x`	Yes	Running variable column.
`y`	Yes
`fuzzy`	No	Treatment column for fuzzy RD (optional).
`detail`	No	Payload depth; agent is the fullest.	agent
`data_id`	No	Data handle (d_...) from load_data; replaces data_path.
`data_csv`	No	Small inline table as CSV text.
`as_handle`	No	Cache the fit and return its result_id.
`data_path`	No	Absolute path of a data file on the server.
`result_id`	No	Handle of an earlier fit made with as_handle=true.
`data_records`	No	Small inline table as row objects.
`max_output_bytes`	No	Result byte budget (default 262144; 0 = none).

Output Schema

Name	Required	Description	Default
No arguments

Schema Changelog

Changes observed during successful MCP inspections.

First observedv0.1.0Nov 12, 2026

TDQS

A3.8/5.0

Behavior3/5

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

Annotations already declare readOnlyHint=true and openWorldHint=false, so the safety profile is covered. The description usefully adds that the call produces a PNG image content block plus a markdown report and result_id, but it omits cost/latency expectations for a four-step computation and any failure-mode behavior (e.g., what happens if rddensity is not applicable).

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 dense sentence lists the pipeline order first, then the return shape in a second short clause. There is no filler; every fragment (PNG, McCrary, bandwidth, result_id, image block) carries information.

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?

With an output schema and 92% schema coverage, the description needn't document returns or params in depth, and it does state the output composition. The main remaining gap is guidance on selecting this composite over its constituent tools and noting the input-data requirement, which is a modest shortfall for a 12-parameter pipeline.

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 92%, so the schema already documents the 12 parameters, including the data-source alternatives (data_id, data_path, data_csv, data_records) and as_handle. The description adds no parameter-level meaning beyond naming 'bandwidth' as the rdsensitivity target; baseline 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?

States a specific composite action ('End-to-end RD workflow') and enumerates the exact steps and tools it chains: rdrobust, rdplot, rddensity (McCrary), rdsensitivity. This clearly separates it from the sibling rdrobust, which performs only the first step, and an agent can tell them apart without opening either schema.

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

Usage Guidelines3/5

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

Usage is implied by the name 'pipeline' and the enumerated chain: use this when you want the whole RD analysis in one call. However, it never states when to prefer the individual tools (rdrobust/rddensity) or its prerequisites, such as needing data_id from load_data or a data_path before calling.

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