TakeHome API

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

Annotations already declare readOnlyHint, idempotentHint and destructiveHint=false, so safety is covered. The description goes further by disclosing what is computed and what is returned (net pay per year/month/week, effective and marginal rate, GOV.UK sources), which is genuine behavioral context about output shape and domain coverage. It does not discuss edge cases such as invalid region/taxYear combinations or schema validation failures.

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?

It is a dense two-sentence block that front-loads the core purpose before listing coverage and the alternative-to-manual-calc instruction. Every clause carries information, though the mid-sentence enumeration of tax features is long and could be trimmed slightly.

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 correctly takes on the burden of explaining returns: net pay at three cadences, effective and marginal rate, and source citations. That covers the main gaps for a computation tool with nested params, but the undocumented region and taxYear parameters remain unaddressed.

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 0% across 6 parameters (one a nested object), so the description must compensate. It does name the three pension methods ('salary sacrifice, net pay, relief at source') and mentions student loans and the child benefit charge, mapping to the pension, studentLoans and childBenefitAnnual fields. But it says nothing about region values, taxYear options, or grossSalary units/limits, leaving several parameters undocumented in both places.

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 opens with a specific verb+resource+scope: 'Exact UK take-home pay for one employee', and enumerates the exact deduction categories computed (income tax by band, NI, student loans, pension, 60% trap, HICBC). The phrase 'for one employee' implicitly separates it from the sibling compare_take_home, which presumably handles multiple.

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 gives an explicit directive: 'Use this instead of calculating UK deductions yourself', which is clear context for when to reach for it. However, it never names or contrasts with the siblings compare_take_home or get_tax_rates, so the routing decision between the three is left to inference.

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 declare readOnly, idempotent, non-destructive and closed-world, so the safety profile is covered. The description adds useful behavior: the scenario-count bound and the fact that results are expressed as a difference in net pay from the first scenario. It does not cover error cases (e.g., what happens below 2 scenarios).

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 dense sentence that front-loads the verb and scope, then layers in the enumerated scenario types and the output framing with zero filler.

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 does the work of explaining the return shape ('the difference in net pay from the first'), which is the key thing an agent needs. It is nearly complete, missing only guidance on the single-scenario sibling and per-field semantics.

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 0%, and the description compensates partially by naming the scenario dimensions (pension changes, Scotland, student loans) that map to nested fields. However, it says nothing about taxYear, pension method enum, childBenefitAnnual, or the region codes, leaving several properties to be inferred from the schema alone.

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 (Compare) and resource (UK pay scenarios), plus the bounds (2 to 5) and the scenario types covered (pay rises, pension changes, region moves, student loans). It implicitly distinguishes itself from calculate_take_home by being multi-scenario, but never names the sibling outright.

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 examples of scenario types give implied context for when to reach for this over a single calculation, but there is no explicit when-to-use rule or when-not guidance naming calculate_take_home as the single-scenario alternative.

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 declare readOnlyHint=true, idempotentHint=true, destructiveHint=false and openWorldHint=false, so the safety profile is fully covered by structured data. The description adds only the 'Free' cost signal and the coverage of data returned; it says nothing about response format or the default year when taxYear is omitted.

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?

Compact and front-loaded: the returned datasets come first, with year scope and cost at the end. No filler, though the fragmentary 'Free.' reads as a tacked-on tag rather than integrated 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?

With no output schema, the description usefully enumerates the categories of data returned (tax bands, NI, student loans, child benefit charge), which is what an agent needs to decide if this tool answers its question. Format and default-year behavior remain unspecified, a minor gap for a one-parameter read tool.

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 0% for the single taxYear parameter, but the enum already constrains it to 2025-26/2026-27. The description repeats those years rather than adding new meaning, and does not state what happens if the optional parameter is omitted (required count is 0).

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 resource it returns — income tax bands for England/Wales/NI and Scotland, National Insurance, student loan thresholds and the child benefit charge for a UK tax year. That is specific enough to distinguish it from the calculate_take_home and compare_take_home siblings, which the description implies but never names outright.

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 explicit statement of when to use this tool versus the two calculator siblings. The content list implies it is a reference-data lookup, but nothing says whether it should be called before/alongside calculate_take_home, or whether it is the source of rates those tools use.

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