UK Statutory Sick Pay and Maternity Pay

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

Annotations already declare readOnly/idempotent/non-destructive/closed-world, so the bar is lower, yet the description adds real behavior: the 39-week week-by-week output structure, the two-tier rate formula, uprating switchover rules, and data provenance (gov.uk, fetched 2026-11-02). It does not say what happens when the employee fails the 26-week service or LEL test — error, zero pay, or a flag — which is the main remaining behavioral gap.

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 core calculation and the rate structure, with no filler sentences; the provenance note is short and earns its place. It is dense and long-ish, but every clause carries substantive information.

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 4-parameter, no-output-schema tool, the description adequately conveys the return shape (week-by-week over 39 weeks) and the statutory logic. The only shortfall is unspecified behavior for ineligible inputs, which an agent would need to interpret results 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%, so all four parameters are already documented, including the smp_start_date default of the due date. The description explains derived concepts (qualifying week, LEL) but adds no format or constraint detail beyond the schema, so 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?

States a specific verb and resource ('Works out UK Statutory Maternity Pay week by week for 39 weeks') and immediately scopes the calculation model. It is clearly distinct from the siblings (sick pay, eligibility check, minimum wage rates), so an agent can select it without opening the schema.

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 by the calculation description, and the note that 'Same structure applies to Statutory Adoption Pay' hints at a related case. However, there is no explicit when-to-use guidance or routing versus check_eligibility, which overlaps with the qualifying-week and lower-earnings-limit facts this tool computes.

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

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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive, closed-world), and the description adds substantial context beyond them: rule versioning by start date, the 28-week cap, HMRC unrounded daily rates, transitional SI 2026/373 handling, and a rate-fetch timestamp caveat that tells the agent figures may be stale. It stops short of describing the response shape, e.g. whether the transitional rules produce a separate output field or a flag in the result.

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 core purpose, then progressively narrower detail on rates and transitional rules; every sentence carries factual weight. It is one dense block, though, and the rate/versioning details could be broken out for faster scanning, and the fetched-on timestamp could be trimmed to a shorter caveat.

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 pure-computation tool with no output schema, the description supplies the calculation basis, both rule regimes, the cap, and the data provenance needed to trust and call it. The remaining gap is what the agent gets back (a figure alone, or a breakdown with the applied regime and transitional flag).

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 a 3 would be the baseline, but the description adds real semantics: it explains that average_weekly_earnings is used for the 80% test and that start_date selects the rule regime, both of which link inputs to computation logic. It does not elaborate on how days_off interacts with calendar_days_sick beyond what the schema 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?

Opens with a specific verb+resource ('Works out UK Statutory Sick Pay') for a clearly bounded scope ('for a period of sickness'). The domain is distinct from all three siblings (maternity pay, eligibility check, minimum wage rates), so an agent can route to it without opening the schema.

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 description makes clear which temporal scenario selects which rule set (starts on/after 6 April 2026 vs 6 April 2025–5 April 2026), which is the key usage determinant. It does not explicitly name alternatives or exclusion cases (e.g. 'use check_eligibility first to determine qualification'), so routing against siblings is left implicit.

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

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

Annotations already cover safety (readOnly, idempotent, non-destructive, closed-world), yet the description still adds substantial behavior: tri-state results including a 'not checkable' outcome, the qualifying-week rule for the 26-week test, the 2026 SSP changes, the applicable lower earnings limits, and data provenance with a fetch date.

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 purpose and return shape, and the dense rule detail (dates, thresholds, SSP 2026 changes) is genuinely useful context rather than filler. It runs long as a single sprawling sentence and could be split for scanability.

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 an 8-parameter tool with no output schema, the description does the necessary work: it names the decision output, the rule set applied, and the data vintage. The return value is only loosely characterized ('the weekly amounts'), leaving the agent to infer exact fields.

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 baseline is 3; the description earns above that by explaining the logic behind key inputs — the 26 weeks into the qualifying week for employment_start and due_date, and the LEL threshold applied to average_weekly_earnings. It still doesn't clarify what the returned 'weekly amounts' are relative to.

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 (checks qualifying conditions) and a precisely scoped resource (five named UK statutory pay types), and describes the return shape (per-condition tri-state plus weekly amounts). This is clearly distinguishable from the calculate_* siblings, which compute amounts rather than eligibility.

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 description makes the eligibility-checking purpose clear but never says when to prefer this over calculate_statutory_sick_pay or calculate_statutory_maternity_pay, even though it also returns weekly amounts, which creates overlap ambiguity. Usage is implied by the payment_type enum rather than stated.

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

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

Annotations already cover read-only, idempotent, closed-world and non-destructive, so the description is free to add genuinely new facts: the exact rate years held (2024–2027), the published future figures, and data provenance/currency ('fetched from gov.uk on 2026-11-02'). It does not spell out behaviour for dates outside the covered years, which is the main remaining ambiguity.

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?

Purpose and scope are front-loaded in the first clause, but the parenthetical enumerating specific figures (£12.71, £10.85, £8, £13.21, £11.27, £8.31) is payload data that belongs in the response, not the selection description. Those tokens cost attention without helping the agent decide whether to call the tool.

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 carries the burden of describing returns, and it does: hourly rates per age band, apprentice rate, the applicable rate, and optional weekly/annual pay. Provenance is disclosed. The only gap is behaviour for a date outside the 2024–2027 coverage window.

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 adds real meaning beyond the schema: it explains the age→band mapping outcome, that apprentice interacts with the age band, and that hours_per_week produces weekly and annual pay. That explains the result of combining parameters rather than restating field definitions.

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 ('Returns the UK National Living Wage and National Minimum Wage hourly rates') plus scope qualifiers: in-force-on-a-date, by age band, apprentice rate, and the applicable rate for a given age. It also names the secondary output (weekly/annual pay at the rate), which clearly separates it from the statutory-pay calculator siblings.

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?

It makes the call conditions clear: supply a date to pick the in-force table, an age to get the applicable rate, and hours_per_week to get derived pay. It never names an alternative tool or an exclusion ('do not use for statutory sick/maternity pay'), so it stops short of explicit when-not guidance.

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