Causal Decision Agent

Overview Schema Source Related Servers Discussions Admin

design_robust_event_study

Read-only

Diagnose negative-weight contamination in staggered event-study designs and flag affected horizons, guiding robust estimation choices.

Instructions

Design-robust event study with explicit negative-weight diagnostics per cohort x relative-time cell. Reports which event-study coefficients receive negative weights in TWFE and flags the affected horizons. Assumptions: Parallel trends across cohorts; treatment effects may be heterogeneous across cohort and time; No anticipation prior to the event time; Implicit TWFE comparison weights are non-negative (negative-weight contamination is diagnosed, not assumed away). Pre-conditions: Long-format panel with y, treat, time, id (same conventions as callaway_santanna); Staggered/variable treatment timing so the per-(cohort, time) weight diagnostic is meaningful; Event-time window (leads, lags) contained within observed pre/post coverage. Failure modes: model_info weights show large negative TWFE weights flagging forbidden comparisons -> Drop already-treated controls and use a heterogeneity-robust staggered estimator instead of TWFE; Too few treated units per cohort-time cell to identify weights or SEs -> Coarsen the event-time window or pool cohorts to raise per-cell counts. Alternatives: sp.sun_abraham, sp.bacon_decomposition, sp.cohort_anchored_event_study, sp.callaway_santanna. Typical...

Input Schema

TableJSON Schema

Name	Required	Description	Default
`y`	Yes	Outcome variable column name or outcome array.
`id`	Yes	Unit, subject, or panel identifier column.
`lags`	No	lags parameter (int).
`time`	Yes	Time period column.
`alpha`	No	Significance level for confidence intervals and tests.
`leads`	No	leads parameter (int).
`treat`	Yes	Treatment indicator or first-treatment-period column.
`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
`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.
`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?

Beyond the readOnlyHint annotation, the description discloses key behavioral assumptions (parallel trends, heterogeneity, no anticipation), explains that negative-weight contamination is diagnosed rather than assumed away, and details failure modes with concrete remedial actions. This is substantial transparency about how the tool behaves and what its outputs imply.

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 well-structured with clear Assumptions, Pre-conditions, Failure modes, and Alternatives sections. It is dense but relevant. The main flaw is the trailing incomplete 'Typical...' section, which slightly weakens the structure and leaves an unfinished thought.

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 complex estimator with 14 parameters, the description covers assumptions, data requirements, failure modes, and next-step alternatives. Since an output schema exists, the description does not need to restate return fields. The tool is described thoroughly enough for an agent to invoke it correctly and plan subsequent actions.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The input schema already describes all 14 parameters with 100% coverage, so the baseline is 3. The description adds meaningful extra context by tying y, treat, time, and id to callaway_santanna conventions and by explaining why leads/lags and cohort-time cell sizes matter for the diagnostics. It does not add per-parameter detail for every field, but it compensates where it matters most.

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 purpose: a design-robust event study that reports negative-weight diagnostics per cohort x relative-time cell and flags affected horizons. This is a concrete verb+resource statement that clearly differentiates the tool from generic event-study or TWFE tools by its diagnostic focus.

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?

The description provides explicit pre-conditions (long-format panel, staggered treatment timing, event-time window coverage) and lists relevant alternatives such as sun_abraham and callaway_santanna. It also gives failure-mode routing advice. It does not fully spell out when each alternative should be chosen over this tool, but it gives enough contextual guidance for a capable agent.

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

Deploy Server