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

Annotations already declare the safe read profile (readOnlyHint, idempotentHint, destructiveHint false). The description adds substantial context beyond that: the exact-to-the-cent accuracy guarantee, the list of returned fields, the method-change rationale (Payday Super), the ATO sourcing caveat and non-advice disclaimer, and the throw-on-out-of-range-date behavior. This is genuinely informative and consistent with the annotations — no contradiction.

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?

Purpose is front-loaded in the opening sentence, followed by returns, then the critical method caveat, then scope constraints. It is on the longer side, but every sentence carries distinct information — the Payday Super warning, the qualifying-earnings boundary, and the date constraint all earn their place. No filler or tautology.

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?

Despite lacking an output schema, the description compensates by enumerating the return values (SG, rate, capped earnings, financial year). It also covers accuracy, temporal scope, error behavior, and legal caveat — everything an agent needs to invoke and interpret the tool correctly. No output schema or sibling routing gaps remain.

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 both parameters are already documented (qualifyingEarnings amount with example; asAt format and default). The description contributes one useful caveat — that the tool does NOT define what counts as qualifying earnings and trusts the supplied figure — which clarifies the parameter's scope. Otherwise it mostly restates schema content, matching the baseline for full coverage.

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 (compute), a specific resource (Australian Superannuation Guarantee), and the exact input basis (qualifying-earnings amount). The precision guarantee ('exact to the cent') and distinct domain clearly separate it from all siblings, which concern awards, GST, entity names, email verification, and crawler access — none overlap with SG calculation.

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 strong temporal context: the tool computes the current way (post-1 July 2026 Payday Super basis) and explicitly warns that old quarterly-OTE code is now wrong, so an agent knows not to reach for legacy methods. It also scopes usage to 'Current financial year only; an out-of-range date throws.' It names no sibling alternative, but none of the listed siblings is a relevant SG fallback, so this is a minor gap rather than a routing omission.

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