Skip to main content
Glama

Check a PAYE tax code

check_tax_code
Read-only

Check whether a UK PAYE tax code (e.g. 1257L, BR, K475, 1257L W1/M1) looks right for a salary and circumstances, explain what it means, and estimate any over- or under-payment. Flat-rate codes (BR, D0, D1) are only judged when hasMultipleJobs is known; without it the verdict is needs_info. Returns a verdict tier; refund figures are estimates, not amounts owed.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "taxCode": "<taxCode>",
      "grossSalary": "<grossSalary>"
    },
    "name": "check_tax_code"
  }
}

Input Schema

NameRequiredDescriptionDefault
taxCodeYesThe code as printed on a payslip or P45
taxYearNoTax year the code applies to; defaults to the current one
scotlandNoTrue for a Scottish taxpayer
grossSalaryYesAnnual gross pay from this job, in pounds
monthsOnCodeNoFor emergency codes: how many monthly payslips were paid on it so far
hasCompanyCarNo
hasMultipleJobsNoWhether the person has another job or pension; omitted when unknown
hasMarriageAllowanceNo
receivesStatePensionNo
otherBenefitsInKindValueNoAnnual taxable value, in pounds, of any employer benefits in kind other than a company car, as listed in the deductions on an HMRC tax code notice (P2) or a P11D. Omit if none.
marriageAllowanceDirectionNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed2 schema fields changed
    • removedInput schema / properties / hasPrivateMedical
      Removed value: -{
      -  "type": "boolean"
      -}
    • addedInput schema / properties / otherBenefitsInKindValue
      Added value: +{
      +  "description": "Annual taxable value, in pounds, of any employer benefits in kind other than a company car, as listed in the deductions on an HMRC tax code notice (P2) or a P11D. Omit if none.",
      +  "maximum": 1000000,
      +  "minimum": 0,
      +  "type": "number"
      +}
  2. First observed

TDQS

A4.4/5.0
Behavior4/5

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

Annotations already declare readOnlyHint=true, destructiveHint=false and openWorldHint=false, so safety is covered; the description adds genuinely new behavior: a verdict tier is returned, and refund figures are explicitly estimates rather than amounts owed. The needs_info fallback for flat-rate codes without hasMultipleJobs further discloses uncertainty handling. It stops short of describing the verdict tier vocabulary or the shape of the explanation.

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

Conciseness5/5

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

Four tightly packed sentences, front-loaded with purpose, then the flat-rate exception, then the return caveat. No filler and no repetition of the title or annotations.

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?

With no output schema, the description does the necessary work of telling the agent what comes back (verdict tier plus estimate) and warns that refund figures are estimates. For an 11-parameter tool it leaves a handful of optional inputs to their schema text, which is acceptable given those fields are documented there.

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 coverage is a middling 64% across 11 params, and the description compensates selectively by explaining the semantic role of hasMultipleJobs (including that it is omitted when unknown) and the accepted tax-code syntax. Several optional inputs (monthsOnCode, hasCompanyCar, marriageAllowanceDirection, scotland, taxYear) get no mention, so the schema still carries much of the load.

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 names a specific verb and resource (check a UK PAYE tax code) and enumerates what the tool produces: a verdict, an explanation of the code, and an over/under-payment estimate. It even gives concrete code formats (1257L, BR, K475, 1257L W1/M1), so an agent can tell this apart from siblings like calculate_take_home_pay or get_tax_position without opening any schema.

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?

It states a clear conditional rule for usage: flat-rate codes (BR, D0, D1) are only judged when hasMultipleJobs is known, otherwise the result is needs_info. That is real when-to-expect-inconclusive guidance, but it never names an alternative sibling tool or an explicit when-not-to-use case.

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

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.