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

Annotations already declare readOnlyHint, idempotentHint, destructiveHint=false and closed-world, so the safety profile is covered by structured data. The description does add real behavioral content beyond that: it never estimates, returns status "missing" with the full list of needed inputs instead of partial results, and returns formulas with citations and attorney-review flags plus a not-legal-advice notice. That is useful, but it is stacked on top of already-complete annotations rather than compensating for a gap.

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?

A single dense paragraph that front-loads the three kind definitions, then scope, engine provenance, missing-input behavior and return contents in descending order of importance. Every sentence carries information; nothing is boilerplate.

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?

For a calculation tool with no output schema, the description does the necessary work of describing return contents (figures, rate year, formulas with citations, notice) and failure behavior. Minor gaps remain, such as whether disability_percent omitted for kind "partial" simply triggers the missing status — that is implied but not stated.

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 80%, so the schema already documents each parameter, and the description goes further by explaining how each `kind` consumes the parameters — two-thirds of AWW bounded by max/min (with sub-minimum wages paid in full) for total, the same bounds at a degree of disability for partial, and two-thirds of wage loss capped at max but never floored at min for reduced_earnings. That materially clarifies when disability_percent and current_weekly_earnings are required.

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?

States a precise verb+resource ('A weekly benefit rate under the NY Workers' Compensation Law') and enumerates the three calculation modes with their underlying formulas, so an agent knows exactly which computation is performed. It does not explicitly differentiate itself from siblings such as get_max_min_rate or calculate_aww, even though it depends on the same statutory bounds.

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?

Gives a clear scope restriction ('New York State only') and maps each `kind` value to the situation it serves (total vs. partial with a disability degree vs. reduced earnings with current wages). It also states the missing-input behavior, but never names an alternative tool for the adjacent jobs (computing AWW, looking up max/min rates).

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