functional_form_test

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

Annotations already set readOnlyHint=true, but the description goes far beyond that. It discloses known limitations (low power with few units, asymptotic SEs, no bootstrap variant), assumptions (Callaway-Sant'Anna identification, no anticipation), and failure modes (degenerate influence functions). This is exemplary behavioral disclosure beyond the structured fields, with no contradictions.

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 well-structured with clear labeled sections (Validation, Known limitations, Assumptions, Pre-conditions, Failure modes). It front-loads the core purpose and then systematically adds operational detail. While it could be trimmed slightly, every sentence earns its place by conveying critical interpretive guidance.

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 (26 parameters, output schema present), the description covers assumptions, pre-conditions, failure modes, limitations, and interpretation caveats. It is fully self-contained for an agent to decide when to call it and how to interpret results. The output schema handles return-value documentation, so nothing essential 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 baseline is 3. The description adds meaningful context for key parameters: n_bins ('too coarse a grid buys a large p-value for nothing' plus the 'auto' rule), binpoints (explicit edges, padded), and detail (payload depth rationale). It does not explain every parameter, but it enhances understanding of the ones most likely to affect results, which lifts it above the baseline.

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 states a specific verb ('test'), a precise resource (the functional form of the outcome), and the exact methodological question (whether parallel trends hold for every strictly monotonic transformation). It distinguishes itself from sibling tests by naming the Roth & Sant'Anna (2023) approach and the binned Callaway-Sant'Anna machinery. This is unambiguous and clearly differentiated.

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 provides explicit pre-conditions ('staggered or single-cohort panel with never-treated or not-yet-treated controls; outcome with enough support to bin') and warns against misinterpreting large p-values. It also describes failure modes and how to address them (lower n_bins or supply binpoints). While it does not name alternative tools for the 'when not to use' case, the context is strong enough for an agent to decide applicability. A small deduction for not explicitly comparing to sibling functional-form tests.

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