StatsPAI

pipeline_did

Read-only

Runs a complete difference-in-differences diagnostic pipeline on a dataset to check whether the estimated treatment effect is real, returning a markdown report and primary result ID.

Instructions

End-to-end DID workflow: preflight -> did/CS estimator -> audit -> honest-DID sensitivity -> bacon decomposition -> brief. Returns one markdown report + the primary result_id. Use this when the user pastes a DID dataset and asks 'is the effect real?' -- the pipeline runs every diagnostic the literature expects.

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": {
      "time": "<time>",
      "treat": "<treat>",
      "y": "<y>"
    },
    "name": "pipeline_did"
  }
}

Input Schema

Name	Required	Description	Default
`y`	Yes	Outcome column.
`id`	No	Unit id (panel) -- required for staggered-DID.
`time`	Yes	Time column.
`treat`	Yes	Binary treatment indicator.
`cohort`	No	First-treatment cohort column. When supplied, dispatches callaway_santanna instead of classic 2x2 did.
`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.
`covariates`	No
`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

A4.2/5.0

Behavior4/5

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 adds the material fact that this is a chained multi-stage run producing one markdown report plus a primary result_id. It does not mention runtime cost or how partial-stage failures are handled, which matters for a pipeline that 'runs every diagnostic'.

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?

Three sentences, front-loaded with the workflow chain, then the return shape, then the selection trigger. No filler; every clause carries information an agent needs.

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?

For a 14-parameter tool with an output schema and annotations, the description covers purpose, the stage sequence that justifies its cost, the return contract, and the selection trigger. Remaining gaps (expected runtime, behavior on a failing stage) are secondary but would help an agent decide whether to spend a full pipeline run.

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 93% and every parameter is documented in the schema, including the cohort dispatch to callaway_santanna and the as_handle/result_id caching contract. The description itself adds no parameter meaning beyond the schema, so the 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 action (end-to-end DID pipeline) and enumerates the exact stages executed (preflight -> estimator -> audit -> sensitivity -> bacon -> brief). This clearly distinguishes it from the sibling single-stage tools (did, audit, brief, honest_did, bacon_decomposition) that it composes.

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?

Gives an explicit trigger: 'use this when the user pastes a DID dataset and asks is the effect real?'. The stage list implicitly maps to narrower siblings, so an agent can infer when to pick a single-stage tool instead, but no when-not-to-use rule or cost tradeoff is stated outright.

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