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

Annotations already cover the safety profile (readOnly, non-destructive, closed-world), so the description's job is to add context, which it does: it discloses that results are gross (pre-tax), that they are estimates only, and that the computation mirrors the AuraCalcs website formula. The enumerated output periods also tell the agent what comes back despite there being no output schema. It does not explain how the aliased inputs (hourly vs hourlyRate) interact.

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?

Three short sentences, front-loaded with what is converted and to which periods, followed by provenance and two caveats. No filler and nothing redundant — each sentence carries a distinct fact.

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 9-parameter, all-optional calculation tool with full schema coverage and no output schema, the description supplies scope, output periods, and the gross/estimate caveats — enough to call it correctly. The one gap is the parallel alias inputs (hourlyRate, hoursPerWeek, weeksPerYear), whose conflict/precedence behavior is unaddressed in both the schema and the description.

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%, including defaults and ranges for every parameter, so the baseline of 3 applies. The description mentions overtime (mapping to ot/otx) but adds no syntax, precedence rules for the duplicate alias fields, or guidance on the unpaidWeeks vs weeks interaction beyond what the schema already states.

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 verb ('convert') and resource ('hourly wage') and enumerates the output periods (annual, monthly, semimonthly, biweekly, weekly, daily), so the transform is unambiguous. The line 'This is gross pay before tax' implicitly separates it from the sibling calculate_paycheck, but the alternative is never named, so sibling differentiation is inferred rather than stated.

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?

'This is gross pay before tax' and 'Estimate only' function as soft exclusions — an agent knows not to use this for take-home/net questions — but there is no explicit when-to-use rule and the sibling calculate_paycheck is never mentioned or contrasted. Usage is only implied from the stated scope.

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