Causal Decision Agent

Overview Schema Source Related Servers Discussions Admin

staggered_cs

Read-only

Estimates causal effects with Callaway-Sant'Anna weights when treatment timing is randomly assigned, using design-based inference for valid standard errors.

Instructions

Callaway-Sant'Anna's estimand with design-based inference (Roth & Sant'Anna 2023). Same weights as sp.callaway_santanna -- every not-yet-treated cohort is a control -- but the standard error comes from random adoption timing rather than parallel trends. Use when timing was randomised and you want the familiar CS estimand; use sp.callaway_santanna when it was not. Units already treated in the first period are dropped, since ATT(g,t) is not identified for them. Validation: validated evidence tier (known-truth, reference, external-parity, or Monte Carlo artifact). Do NOT use when: adoption timing was not randomised -- use sp.callaway_santanna, whose inference rests on parallel trends instead. Assumptions: treatment timing is randomly assigned; balanced panel. Pre-conditions: balanced panel with at least two cohorts. Alternatives: sp.staggered_rollout, sp.staggered_sa, sp.callaway_santanna. Typical minimum N: 50.

Input Schema

TableJSON Schema

Name	Required	Description	Default
`g`	Yes	First-treatment period; never-treated may be 0, NaN or inf
`i`	Yes	Unit identifier
`t`	Yes	Time period
`y`	Yes	Outcome variable column name or outcome array.
`alpha`	No	Significance level for confidence intervals and tests.
`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
`fisher`	No	fisher parameter (bool).
`se_type`	No	Conservative bound, or the adjusted SE R staggered prints	neyman
`estimand`	No	Weighting scheme, as in sp.staggered_rollout	simple
`n_fisher`	No	Number of fisher.
`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.
`event_time`	No	event_time parameter (float or list).
`data_columns`	No	Optional column projection. Parquet/Feather/Stata loaders honour this for fast partial reads.
`random_state`	No	Random seed or RandomState for reproducible stochastic steps.
`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

A4.6/5.0

Behavior5/5

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

Annotations already declare readOnlyHint=true, and the description adds meaningful behavioral context beyond that: the inference is based on random adoption timing, units already treated in the first period are dropped, balanced panel is required, and at least two cohorts are needed. There is no contradiction with the annotations.

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, front-loaded, and well-structured, but it contains some repetition between the 'Use when' and 'Do NOT use when' statements and a somewhat generic 'Validation:' sentence that adds little actionable guidance. Overall it is appropriately sized for a complex estimator.

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 17-parameter estimator with a complete schema and output schema, the description supplies the crucial selection context: randomised timing requirement, familiar CS estimand, control definition, dropped units, assumptions, pre-conditions, and alternatives. An agent has enough information to decide whether to call it and how.

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 input schema fully documents all 17 parameters. The description does not add parameter-specific meaning beyond the schema, so the baseline score of 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 opens with a specific estimand and inference mode, 'Callaway-Sant'Anna's estimand with design-based inference (Roth & Sant'Anna 2023)', and contrasts it with the same weights as sp.callaway_santanna but a different standard error. It also names sibling alternatives, so an agent can distinguish it from closely related tools without inspecting schemas.

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 gives explicit when-to-use and when-not-to-use guidance: 'Use when timing was randomised... use sp.callaway_santanna when it was not' and 'Do NOT use when: adoption timing was not randomised'. It also lists assumptions, pre-conditions, alternatives, and a minimum N threshold, leaving little to inference.

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

Deploy Server