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

Annotations already declare readOnlyHint, idempotentHint, non-destructive and closed-world, so the safety profile is covered. The description adds genuinely new behavioral context: which outputs are produced (nominal vs today's dollars, level annual budget, gap to target, depletion age), that pension eligibility is excluded, that all fields are required, and the global unit conventions.

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?

Front-loaded with the verb and the two phases of the model, and every clause carries information. The first sentence is long and densely parenthetical, which slows scanning, but nothing is filler.

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 17-parameter calculator with no output schema, the description enumerates the return values explicitly and flags the one non-obvious exclusion (pension eligibility). Combined with 100% schema coverage, an agent has everything needed to invoke it correctly.

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% and every parameter carries min/max plus prose, so the schema does the heavy lifting. The description adds only a global convention ('amounts in AUD, rates in percent per year') and the pension-as-input caveat, which largely restates what agePension's own schema text already says.

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 ('Projects') and a specific resource (Australian superannuation balance) with the full modeling scope spelled out — accumulation phase (contributions, tax, caps, fees, inflation) then retirement spending (budget, gap to target, depletion age). The Australian-super domain also implicitly separates it from calculate_uk_pension_drawdown and calculate_retirement_income_gap.

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?

Scope exclusions are given ('The Age Pension amount is an input; eligibility is not calculated', and the schema note that employerRate is 'not a payroll liability calculation'), which tells the agent what this tool will not do. However, there is no explicit when-to-use guidance or routing to the sibling calculators, so the agent must infer selection from the domain name alone.

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