StatsPAI

did

Read-only

Estimate difference-in-differences treatment effects for two-period or staggered panel data, with automatic method selection and support for Callaway-Sant'Anna, Sun-Abraham, BJS, SDID, and DDD.

Instructions

Difference-in-differences dispatcher. 2x2 (two periods, 0/1 treat) when id is omitted; with id, a 0/1 indicator on a multi-period panel is converted to first-treatment cohorts and Callaway-Sant'Anna runs. Pass method= to force '2x2', 'cs', 'sa', 'bjs', 'sdid' or 'ddd'. Validation: validated evidence tier (known-truth, reference, external-parity, or Monte Carlo artifact).

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": "did"
  }
}

Input Schema

Name	Required	Description	Default
`y`	Yes	Outcome column
`id`	No	Unit identifier; required for staggered designs (method='cs'/'sa'/'bjs') and SDID
`time`	Yes	Time period column
`treat`	Yes	Binary treatment indicator (0/1) or first-treatment period column (0 = never treated)
`detail`	No	Payload depth; agent is the fullest.	agent
`method`	No	Estimator (see sp.describe_function('did')).	auto
`parity`	No
`cluster`	No	Cluster column for cluster-robust SEs
`data_id`	No	Data handle (d_...) from load_data; replaces data_path.
`data_csv`	No	Small inline table as CSV text.
`subgroup`	No	Affected-subgroup column (method='ddd' only)
`as_handle`	No	Cache the fit and return its result_id.
`crit_dist`	No
`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	Optional control columns
`aggregation`	No	Callaway-Sant'Anna aggregation of ATT(g,t)
`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

A3.7/5.0

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 real behavioral context beyond that — automatic conversion of a 0/1 panel indicator into first-treatment cohorts, the method-forcing override, and a validated-evidence-tier requirement. It stops short of describing how data must be supplied or what happens on conflicting inputs (e.g., both data_id and data_path).

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?

Three front-loaded sentences with no filler, lead sentence establishing the tool's role immediately. Minor cost: heavy shorthand ('2x2', 'cs', 'sa', 'bjs', 'ddd') is used before the reader has the enum mapping, which slightly taxes comprehension.

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 19-parameter tool with an output schema and annotations, the description supplies the essential dispatch logic and validation gate; the remaining parameters (data_id, data_path, data_csv, result_id, as_handle) are documented in the schema. It would be stronger if it named the data-input pathway or handle-reuse pattern, but nothing critical to correct invocation is absent.

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 coverage is 89%, so the schema already carries most parameter meaning and baseline is 3. The description reinforces the id/time/treat interplay and lists forceable methods, but that list omits several schema enum values (auto, callaway_santanna, sun_abraham, staggered_rollout), making it a partial rather than additive explanation.

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?

Opens with a specific verb-and-resource label ('Difference-in-differences dispatcher') and then spells out the two dispatch modes: 2x2 when id is omitted, Callaway-Sant'Anna when it is supplied. An agent can distinguish the core behavior from siblings like callaway_santanna or sdid, though the description never explicitly contrasts itself with those named alternatives.

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?

Gives conditional guidance for the estimator path (omit id for 2x2, provide id for staggered/CS, pass method= to force a specific estimator) and states a validation-tier precondition. However, it never says when to call this tool rather than the dedicated callaway_santanna or sdid siblings, leaving the dispatcher-vs-specialist choice to inference.

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

did