cohort_anchored_event_study

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

Beyond the readOnlyHint annotation, the description discloses key behavioral details: cluster-robust standard errors with no parallel-trends protection, cohort-anchored rather than pooled TWFE identification, and explicit assumptions such as no anticipation and absorbing treatment. It also lists failure modes, giving the agent useful information about when results will be invalid.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is dense but organized into purpose, contrast with alternatives, assumptions, pre-conditions, and failure modes. Every section adds actionable information, and the core purpose is front-loaded before the assumptions and constraints.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the estimator's complexity and the crowded event-study sibling space, the description covers what the tool does, what it is not, when to use an alternative, assumptions, data pre-conditions, and failure modes. The output schema exists, so return-value description is not required, and the input schema covers parameters.

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

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

Input schema coverage is 100%, so the baseline is 3, but the description adds real parameter meaning: it clarifies that treat encodes the first treatment period with 0 = never-treated, that id and time define a long-format panel, and that leads/lags define a requested event-time window. This goes beyond the schema's generic descriptions.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description opens with the specific estimator name and explains exactly what it computes: separate event-study paths per cohort aggregated with cohort weights, explicitly contrasted with averaging across cohorts at each relative-time bin. It distinguishes itself from Liu (2025)'s robust-inference procedure and from honest_did, so an agent can differentiate it from closely related siblings.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description gives explicit when/when-not guidance: it is the cohort-anchored starting estimator, not the block-bias robust-inference procedure, and for parallel-trends sensitivity the agent should use sp.honest_did. Assumptions and pre-conditions further constrain when the tool is appropriate, including never-treated cohorts and absorbing first-treatment events.

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