Skip to main content
Glama

reference-data

by dev.afriref

compute_payroll

PAID ($0.10). Gross-to-net take-home pay for Nigeria or Kenya: applies PAYE (on the verified brackets) plus the statutory employee deductions (Nigeria: pension/NHF/NHIS; Kenya: NSSF/SHIF/Affordable Housing Levy) and reliefs, returning net pay with full workings, per-contribution citations and DISCLOSED assumptions. Nigeria's pension base needs pay composition — pass basic/housing/transport for an exact figure, or a market-convention 40/30/10 split is assumed and disclosed. Pass api_key if you have one; otherwise the response explains how to pay via x402.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
basicNoNigeria: basic pay component
grossYesGross pay in local currency
periodNoPeriod the gross covers (default month)
sectorNoNigeria: public applies NHF; private (default) sets NHF 0
api_keyNoAPI key (bypasses x402; metered for invoicing)
countryYesPayroll is supported for Nigeria (ng) and Kenya (ke)
housingNoNigeria: housing allowance
transportNoNigeria: transport allowance
annual_rentNoNigeria: annual rent paid (unlocks rent relief)
nhis_premiumNoNigeria: NHIS employee premium if deducted
pensionable_payNoKenya: pensionable pay for NSSF tiers
insurance_premiumNoKenya: insurance premium for 15% relief

TDQS

A4.3/5.0
Behavior4/5

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

With no annotations provided, the description carries the full burden. It discloses the tool is paid ($0.10), applies PAYE, statutory deductions, reliefs, and returns net pay with workings and assumptions. It also explains the pension base splitting and api_key usage. This is transparent for a payroll tool, though it could mention error handling.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is relatively long but front-loaded with the key purpose. It packs a lot of information efficiently in two sentences, with no wasted words. A more structured format could improve readability, but it remains concise given the complexity.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given 12 parameters, 100% schema coverage, and no output schema, the description is complete enough. It covers the main logic, assumptions, and special cases, and hints that output includes net pay with workings and citations. It compensates for the lack of output schema by describing the return content.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so baseline is 3. The description adds value by explaining the roles of basic/housing/transport for Nigeria's pension base and the 40/30/10 split default, as well as sector differences and api_key purpose. This goes beyond the schema descriptions.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly specifies that the tool computes gross-to-net take-home pay for Nigeria or Kenya, listing specific deductions and reliefs. This distinguishes it from sibling tools like compute_income_tax, which only handle a subset of the payroll computation.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description provides context on when to use the tool (for Nigeria or Kenya payroll) and mentions requirements like providing basic/housing/transport for exact pension base. However, it does not explicitly contrast with alternatives like compute_income_tax, though the purpose implies this is a full payroll tool.

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

All reference-data toolsInspect
Try in Browser
RayrunBuild, deploy, and operate MCP servers without becoming an infrastructure team.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

TDQS

A4.3/5.0
Disambiguation5/5

Each of the 11 tools addresses a clearly distinct operation: compliance checking, income tax, payroll, VAT, working days, holidays, series queries (current/history/snapshot/catalog), and settlement date. Even within the tax and calendar families, the descriptions precisely delineate boundaries, so there is no realistic risk of an agent selecting the wrong tool.

Naming Consistency4/5

The vast majority of tools follow a consistent verb_noun snake_case pattern (check_, compute_, get_, list_, count_). The only deviation is settlement_date, which is a noun phrase rather than verb_noun, but it is still clear and idiomatic. This single outlier prevents a perfect score.

Tool Count5/5

With 11 tools, the server is well-scoped for a reference-data domain covering statutory rates, calculations, calendars, and settlement conventions. Each tool has a distinct purpose and earns its place; the count is neither thin nor bloated.

Completeness4/5

The server provides strong coverage of its stated domain: statutory tax computations, payroll, minimum wage, VAT, holidays, working days, and settlement dates, plus a generic series API for extensibility. Minor gaps exist, such as payroll only supporting Nigeria and Kenya and no standalone social-security contributor, but the response descriptions explicitly disclose these limits, and the generic series endpoint provides a workaround for common lookups.

Resources