cgs_continuous_did

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

Annotations already declare readOnlyHint=true, consistent with an estimation tool. The description adds rich behavioral detail: standard errors from per-cell influence function, how staggered designs aggregate cells with StatsPAI weights, which estimators are pinned against the reference, and that the cck dose estimator is not implemented. It also lists assumptions and failure modes, going well beyond what annotations provide.

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 long but structured logically: core purpose, validation, limitations, assumptions, pre-conditions, failure modes. It front-loads the main purpose and then details constraints. While verbose, it is organized and every section adds value for an econometric tool with this complexity.

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?

With 18 parameters (6 required) and an output schema present, the description covers limitations, assumptions, pre-conditions, and failure modes. It does not explain every parameter but relies on the schema for that. For a complex estimator, it is reasonably complete, though it could explicitly mention how to handle the no-zero-dose case beyond the truncated control_group hint.

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 description coverage is 100%, so all 18 parameters have descriptions. The tool description adds some conceptual framing (e.g., what ACRT means, the role of dose) but does not add significant meaning beyond the schema. Baseline 3 is appropriate.

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 states the tool implements Callaway, Goodman-Bacon & Sant'Anna (2024) DiD for continuous treatments, explains the key concepts (dose, ATT(d), ACRT(d)) and the B-spline regression method. It differentiates itself by focusing on the causal response at dose d, distinguishing it from sibling tools like continuous_did or dose_response.

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?

Provides pre-conditions (panel with continuous dose, zero-dose units, at least one period before each treated cohort), assumptions, and failure modes (no zero-dose units in a cell, use control_group='notyettreate...'). It gives context on when the tool is appropriate but does not explicitly name alternative tools to use instead, relying on the description's specificity to guide selection.

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