Causal Decision Agent

Overview Schema Source Related Servers Discussions Admin

event_study_convention

Read-only

Identify how each difference-in-differences estimator constructs event-study reference periods to resolve disagreements in pre-trend plots. Returns a registry of baseline conventions.

Instructions

Report how each DiD estimator builds its event-study reference periods. Two implementations can agree on every post-treatment coefficient and still plot different pre-trends, because the leads are a separate construction (Roth 2026). Returns the convention registry: what each half of the path is differenced against, whether the two halves are symmetric, and whether the path coincides with a dynamic TWFE event study in a non-staggered design. Failure modes: Estimator name not in the convention registry -> Call sp.event_study_convention() with no argument to list the recorded estimators. Alternatives: sp.compare_event_study_conventions, sp.event_study.

Input Schema

TableJSON Schema

Name	Required	Description	Default
`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
`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`	No	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://.
`estimator`	No	Registry key such as 'callaway_santanna[base_period=varying]', or a bare estimator name for all of its option-specific rows. None returns the whole registry.
`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

A4.2/5.0

Behavior4/5

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

Annotations readOnlyHint=true and openWorldHint=false already signal a safe, closed lookup. The description adds behavioral detail by stating the returned object is a registry rather than fitted estimates, describing its fields, and disclosing the unknown-estimator failure mode. That goes beyond the annotations without contradicting them.

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?

The description is front-loaded with the core claim, then justifies it, lists output contents, and provides failure-mode and alternative actions in a logical order. Every clause earns its place; the Roth citation and registry details are informative, not filler. It is longer than average but tightly scannable.

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?

A registered output schema and full schema coverage lower the burden on the description. The description covers what the registry contains, a failure mode, and a recovery action. The main gap is that data_path, data_columns, and data_sample_n appear in the schema without clarification that this tool is a pure metadata lookup, which could mislead an agent into supplying unnecessary data.

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 all seven parameters are documented in the schema and the description adds no parameter-level meaning. It does not explain, for instance, whether data_path/data_columns are relevant to a registry lookup, which would have added value. Per the baseline rule, 3 is appropriate when the schema does the heavy lifting.

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 verb+resource: 'Report how each DiD estimator builds its event-study reference periods.' It then specifies the exact output (a convention registry) and names two sibling tools, making differentiation effortless. The Roth 2026 aside usefully distinguishes coefficients from leads, reinforcing the tool's unique scope.

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 a concrete failure-mode rule: if an estimator name is not in the registry, call with no argument to list recorded estimators. It also names sp.compare_event_study_conventions and sp.event_study as alternatives. It stops short of stating selecting conditions for each alternative, but the failure-mode guidance is unusually actionable.

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

Deploy Server