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

Annotations already declare readOnlyHint=true and openWorldHint=false, so the safety profile is covered and the description only needs to add context – which it does, disclosing the statutory rate schedule (1.5/1.5/0.5% rising to 6/6/2% by year 10) and the €80,000 earnings cap. It stops short of saying results are illustrative projections driven by default assumptions (charges, pay growth, return), which is the one behavioral caveat an agent would want.

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?

A single front-loaded sentence that leads with the scheme name and date, then the contribution mechanics, then the output. The dense parenthetical is justified because the rates and cap are the core domain facts, though it could be split for readability.

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?

With no output schema, the description must carry the return story, and it does at a high level ('the projected pot at retirement'). However, it omits eligibility bounds that matter for a tool taking age (auto-enrolment age bands) and does not indicate whether the response breaks out employee/employer/State contributions separately or is a single figure.

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 schema already documents all six parameters, including defaults and the note that investReturn is an assumption. The description adds domain meaning to 'salary' by stating the €80,000 cap and contribution percentages apply to pay, but says nothing extra about age, retireAge, or how the year-10 phase-in interacts with the projection horizon. Baseline 3 applies.

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 the exact scheme (Ireland's MyFutureFund auto-enrolment, live from January 2026) and states precisely what the tool computes: the employee/employer/State contribution split and the projected pot at retirement. The scheme-specific naming cleanly separates it from siblings such as ireland_state_pension_contributory or new_zealand_kiwisaver.

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 only implied – an agent can infer this is for someone with an age and salary wanting a MyFutureFund projection. There is no explicit when-to-use framing, no exclusions, and no pointer to related siblings like ireland_state_pension_contributory or ireland_where_to_put_savings.

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