stacked_did

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

Annotations declare readOnlyHint: true and openWorldHint: false. The description adds substantial behavioral context beyond that: it explains the cost of row duplication (O(n x cohorts)), the risk of dropping late-treated units, and the need to check coverage in model_info if no clean controls exist. It does not contradict annotations—the tool is a read-only estimation operation.

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 well-organized: it starts with the core methodology, then caveats, then alternatives and costs. However, it is somewhat long and could be tightened—some information is repeated (e.g., dropping late-treated units appears in both the robustness note and failure modes). Still, every major point is useful and front-loaded.

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 tool's complexity (staggered DiD with multiple cohorts, sub-experiments, memory concerns), the description covers all necessary aspects: method, assumptions, pre-conditions, failure modes, costs, and typical sample size. The output schema is present, so return values are already specified. Nothing critical is missing.

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?

Schema coverage is 100%, so parameters like data_path, y, time, etc. are already documented. The description adds value by explaining the cost implications of window size (narrow window to bound memory), and the never_treated_only parameter's effect on control selection. It doesn't deeply elaborate on every parameter but the schema covers them, so this meets the baseline for high schema coverage.

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 clearly identifies the tool as implementing the stacked DiD estimator with a citation, and explains the core methodology (constructing sub-experiments per cohort, TWFE on stacked panel). It distinguishes itself from alternatives like callaway_santanna and sun_abraham, and even specifies when not to use it (single cohort). This goes beyond a simple verb+resource statement.

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 explicitly states when to use (staggered adoption with >=2 cohorts) and not to use (single cohort), and names concrete alternatives (sp.callaway_santanna, sp.sun_abraham, sp.did_imputation). It also lists failure modes and pre-conditions, giving an agent clear decision rules.

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