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

Annotations already declare readOnlyHint=true and openWorldHint=false, so safety needs no restating. The description adds genuine context beyond them by naming the tax treatment applied to each product (DIRT 33%, exit tax with 8-year deemed disposal, CGT 31%, pension tax relief) and by flagging that market growth is a user-supplied assumption rather than a forecast — an important caveat that shapes how the agent should present results. It stops short of describing the response shape, but with annotations present that gap is minor.

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?

One sentence, front-loaded with the jurisdiction and the comparison action, then a compact parenthetical list of the five vehicles with their tax rates. The assumption caveat closes it out. Nothing is redundant and nothing essential is deferred.

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?

No output schema exists, but the description effectively enumerates the output dimensions by naming all five products and their tax bases, so the agent knows what a result will compare. It could go slightly further on model boundaries — e.g. whether pension drawdown taxation, USC or PRSI are reflected — but for a single-purpose calculator it is nearly sufficient.

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%, so the schema already explains amount, years, growth, depositRate and marginalRate. The description substitutes prose ('a lump sum', 'a number of years', 'an assumption you set') that largely restates the schema and never explicitly ties the 20/40 marginalRate enum or the depositRate default to the modelled outcomes. Baseline 3 is appropriate.

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 and resource ('compare where a lump sum ends up after tax over a number of years') and enumerates the exact vehicles compared: State Savings, bank deposit, ETFs, shares, pension. An agent can distinguish this from siblings like ireland_capital_gains_tax or ireland_myfuturefund_pension, which each cover only one of those pieces.

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?

The comparison framing implies when to use it — a holistic 'where should I put a lump sum' question rather than a single-scheme lookup. However, it never names the sibling tools it supersedes (e.g. ireland_capital_gains_tax, ireland_myfuturefund_pension) or states what this tool does not cover, so routing must be inferred from the product list.

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