Causal Decision Agent

Overview Schema Source Related Servers Discussions Admin

event_study

Read-only

Estimates dynamic treatment effects using relative-time dummies and two-way fixed effects, enabling pre-trend checks and event-time dynamics. Ideal for classical designs with uniform treatment timing.

Instructions

Traditional OLS event-study with entity and time FEs. Generates relative-time dummies around the treatment date, omits a reference period, and estimates via TWFE + optional clustered SE. Exposed for users who want the classical specification alongside CS / SA / BJS; not robust to staggered-effect heterogeneity -- use sp.sun_abraham for that. Validation: certified parity evidence. Do NOT use when: only one pre-treatment period is available -- there are no leads to test parallel trends with, so the plot cannot support a pre-trend claim; treatment timing is staggered and heterogeneous -- a pooled TWFE event study contaminates leads with other cohorts' treated periods; use sp.sun_abraham or sp.callaway_santanna. Assumptions: Parallel trends across event time; No anticipation beyond window lead; SUTVA. Pre-conditions: panel with unit x time x outcome; treat_time column gives first-treatment period (or 0/NaN). Failure modes: Staggered heterogeneity -- TWFE event-study biased -> Use sp.sun_abraham for contamination-robust event-study coefficients. Alternatives: sp.sun_abraham, sp.callaway_santanna, sp.did_imputation. Typical minimum N: 50.

Input Schema

TableJSON Schema

Name	Required	Description	Default
`y`	Yes	Outcome variable column name or outcome array.
`time`	Yes	Time period column.
`unit`	Yes	Unit identifier
`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
`window`	No	(lead, lag) horizons
`cluster`	No	Cluster identifier column for clustered standard errors.
`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.
`covariates`	No	Covariate matrix, DataFrame, or column names.
`ref_period`	No	Reference relative-time period to omit
`treat_time`	Yes	First-treatment period column
`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.

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, so the safety profile is covered. The description goes well beyond this by disclosing failure modes (TWFE bias under staggered adoption), assumptions (parallel trends, no anticipation, SUTVA), pre-conditions (treat_time column semantics), validation status ('certified parity evidence'), and a typical minimum N. It does not contradict the readOnlyHint annotation.

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 long but organized into labeled sections (Validation, Do NOT use when, Assumptions, Pre-conditions, Failure modes, Alternatives, Typical minimum N), making it scannable. There is some redundancy — the staggered-heterogeneity warning appears three times (intro, Do NOT use, Failure modes) — but the complexity of the tool justifies the density.

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 15-parameter estimation tool, the description covers assumptions, pre-conditions, failure modes, alternatives, validation status, and typical minimum N. The output schema exists, so return values need no description. An agent has everything needed to decide whether to call this tool and how to interpret the result.

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 baseline is 3 even without parameter info in the description. The description adds small extras — the ref_period is 'omitted' and treat_time accepts '0/NaN' conventions — but these are marginal beyond the already-detailed schema. This is the weakest dimension, but the schema carries the load.

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 names a specific verb ('estimates'), a specific resource (TWFE event-study with entity/time FEs and relative-time dummies), and explicitly contrasts itself with siblings: 'not robust to staggered-effect heterogeneity -- use sp.sun_abraham for that.' An agent can identify what this tool does and how it differs from sun_abraham or callaway_santanna without opening any schema.

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/when-not-to-use guidance: 'Do NOT use when: only one pre-treatment period is available...' and 'treatment timing is staggered and heterogeneous... use sp.sun_abraham or sp.callaway_santanna.' It also lists alternatives (sp.sun_abraham, sp.callaway_santanna, sp.did_imputation) and states assumptions and pre-conditions. Nothing is left 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