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

Annotations already cover safety (readOnly, idempotent, non-destructive, closed-world), so the description is free to add the things annotations cannot: it names the engine (Comp Desk calc-core, CD.Calc) and asserts it never estimates, discloses the missing-input behavior, states it needs a builder key, and describes what comes back (figures, per-step rule and engine function, not-legal-advice notice). These are concrete behavioral commitments an agent cannot infer from the annotation block.

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 formula and the 1–3 day routing rule are front-loaded and earn their space, but the engine/parity claim is made twice ('Computes with The Comp Desk calc-core, the same engine as the app and the Pro Workspace' and 'Same engine the Pro Workspace tiles call through CD.Calc, so a figure here matches the app to the cent'). It is one dense block rather than structured segments, and the duplicated trust claim costs clarity.

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 no output schema and nine parameters, the description carries the return-shape burden and does so at a summary level (figures, steps with rule and engine function, notice). It also covers the auth requirement and the missing-input path. What remains thin is anything about error or partial-status handling beyond the single "missing" case, which is acceptable for a pure calculation tool.

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 89%, so the baseline is 3, but the description goes beyond it by explaining what each optional input does arithmetically: steady = earnings ÷ days worked × the 200/260/300/365 multiplier for a 4-/5-/6-/7-day week ÷ 52, irregular = earnings ÷ weeks worked, and date_of_accident adds the two-thirds weekly rate clamped within max and min. It stops short of tying every one of the nine parameters (e.g. how tips/board enter the final sum) to its slot, so it is strong rather than exhaustive.

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 specific computation and scope: the NY average weekly wage with tips, board and concurrent wages, computed two ways (steady vs irregular). It also names the sibling it is not ('For a 1–3 day week use calculate_aww') and the jurisdiction ('New York State only'), so an agent can place it against calculate_aww and calculate_weekly_rate without opening a schema.

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 an explicit exclusion with a routing alternative ('For a 1–3 day week use calculate_aww') and an explicit scope limit ('New York State only'). It also states the failure condition up front — a missing input returns status "missing" and nothing is calculated — which tells the agent when the call will not produce figures.

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