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

Annotations already cover the read-only/idempotent/closed-world profile, so the description's job is statutory context — and it delivers: it discloses the age-band formula basis, the 20-year service limit, the weekly-pay cap and its NI variation, and the applicable tax year (2026/27). The worked example ('10 years at 45 on £800/week pays £9,012') conveys the return shape concretely. It does not state the full age-band multipliers, but that is a detail the calculator handles.

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?

Three sentences with no filler, but the ordering is backwards: a specific numeric example occupies the prime front-loaded position while the actual definition of what the tool computes comes second. The trailing URL is a citation, not guidance, though it is short enough not to be harmful.

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 return-value semantics, and the worked example does that in one figure. However, for a 4-parameter statutory calculator it omits the jurisdictional scope statement and regional differences beyond NI, leaving the agent to infer when this tool applies at all.

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% and each parameter carries its own description, so the baseline is 3. The description adds some regulatory meaning — the £751 cap implies pay above that is truncated, and the 20-year limit mirrors the 'years' constraint — but it never explains the region enum (GB-ENG/GB-SCT/GB-WLS/GB-NIR) beyond flagging NI as the £783 outlier.

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 specific resource (statutory redundancy pay) and its defining mechanics: age bands, 20-year limit, and the £751 cap (£783 in NI). The £/NI framing implicitly separates it from the many foreign severance/gratuity siblings (UAE, Saudi, Egypt, Jordan), though it never states the UK-only scope outright. It leads with a worked example rather than a verb, which dampens the opening slightly.

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?

There is no guidance on when to pick this over alternatives, despite a crowded family of severance and pay siblings (gcc_gratuity, saudi_end_of_service, salary_calculator, take_home_pay_calculator). No exclusions, prerequisites, or jurisdictional caveats are given — the agent must infer UK applicability from the currency symbols.

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