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

Beyond the readOnly/openWorld annotations, the description discloses the full modeling rules (3.5% default and employer minimum rising to 4% in April 2028, 25c-per-$1 government contribution capped at $260.72, ESCT on employer contributions, PIR on returns) and flags that the return rate is a user assumption rather than a modeled figure. That is meaningful context about how the answer is derived; it stops short of describing output shape or modelling limits such as contribution holidays or withdrawals.

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 purpose and 2026 rule context are front-loaded in a single sentence, with the important caveat ('Returns are an assumption you set') placed last. The parenthetical rule list is dense but each clause is substantive; only minor tightening is possible.

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 seven-parameter projection tool with no output schema, the description supplies the essential input assumptions and states the computed quantity (balance at 65). It omits what the response contains (single figure vs. breakdown by contributions/returns) and edge-case behavior, which keeps it short of complete.

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 the baseline is 3, but the description earns extra credit by explaining the rule context behind parameters: why employeeRate may be 3.5% now and 4% from April 2028, and that grossReturn is an assumption the caller supplies. It does not separately explain pir or feePct beyond the schema, so it is not a full 5.

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?

The description names a specific resource and scope: KiwiSaver balance at 65 under the 2026 rules, with the exact contribution, government-contribution, ESCT and PIR rules modeled. It is unmistakably a New Zealand retirement-balance projection and cannot be confused with the Ireland/Canada/Australia siblings, although it never uses an explicit verb such as 'calculates'.

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?

Usage is implied rather than stated: an agent can infer this is the tool for projecting a NZ KiwiSaver balance at retirement, but there is no explicit when-to-use/when-not guidance or mention of alternatives. Given the sibling set is other-country calculators, the country prefix does most of the routing work.

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