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

Annotations already cover read-only, idempotent, non-destructive, closed-world, so the description's remaining burden is low; it still adds real context beyond them: it never estimates, a missing required input yields status "missing" with nothing calculated, it requires a builder key, and the response includes per-step rule/engine-function provenance plus a not-legal-advice notice. It does not discuss rate limits, maximum period count, or failure modes beyond the missing-input case.

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 core content is front-loaded, but almost the entire definition is one enormous semicolon-chained sentence that is hard to parse on a first read. It also repeats the provenance claim twice ('the same engine as the app and the Pro Workspace' and 'Same engine the Pro Workspace tiles call through CD.Calc'), which is redundant padding.

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 7-parameter, no-output-schema, domain-heavy calculation tool, it covers what is returned, the missing-input status behavior, the builder-key requirement, and the provenance of the figures. It leaves the maxItems=24 period cap and any behavior on invalid or out-of-range period data to the schema, which is a minor but real gap.

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 86%, so the baseline is 3, and the description earns above that by supplying rule semantics the schema cannot: weeks counted with both ends and the shared boundary day counted once, rounding modes with default tenth, rates clamped to the max/min for the date of accident with RE capped but never raised, amending paid at the prior rate less prior percentage or prior weekly rate, already-paid periods kept in the award but out of money moving and fee, and the three reimbursement scopes. It doesn't add anything for aww, date_of_accident, or ccp_weekly_amount beyond the schema.

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?

Names a specific verb (computes an NY CCP award) plus the exact scope: which period types are supported, what is returned (every period, the award, fee, OC-400.1 amount rounded to $5, both nets), and the jurisdiction (New York State only). It also explicitly differentiates itself from the sibling calculate_ccp_award, calling that the 'simpler TT/TP/RE version', so an agent can pick between the two without opening either 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 clear context for selection: use this full engine when the award involves RE/TR/TP/NCLT/NME/HIA periods, employer reimbursements, amending periods, or the prior-counsel split, versus the simpler calculate_ccp_award. It also states the NY-only restriction and that a missing input returns status "missing" rather than a partial result. It stops short of an explicit 'do not use this for X' exclusion or guidance on when to run calculate_ccp_award first.

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