Skip to main content
Glama

Jaargegevens

set_year_facts
Destructive

Store tax-year facts that documents cannot show—hours criterion, starter status, and wage income—to apply Dutch sole-proprietor deductions and estimate tax to set aside.

Instructions

Facts about a tax year that documents cannot show. hours_criterion: did the owner work at least 1,225 hours in the business (needed for zelfstandigenaftrek). starter: entitled to startersaftrek. wage_income: gross wage from employment that year, used only to estimate how much tax to set aside. Ask the owner; do not assume.

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": {
      "year": "<year>"
    },
    "name": "set_year_facts"
  }
}

Input Schema

NameRequiredDescriptionDefault
yearYes
starterNo
wage_incomeNo
hours_criterionNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

B3.3/5.0
Behavior2/5

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

Annotations declare readOnlyHint=false and destructiveHint=true, so this is a mutating, potentially overwriting operation; the description says nothing about that. It never states what a call replaces or destroys, whether omitted fields are nulled or preserved, or that existing year facts can be lost — a serious gap for a destructive write. The only behavioral guidance offered ('Ask the owner; do not assume') is about sourcing data, not about side effects, so it does not compensate.

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 framing sentence is front-loaded and each following clause maps one-to-one to a parameter, with no filler. The telegraphic, colon-separated format is compact and scannable, though the abrupt field-list style slightly reduces readability compared with full sentences.

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

Completeness3/5

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

There is no output schema, and the description never indicates what is returned or confirmed after a write. Combined with destructiveHint=true and no explanation of overwrite/replace semantics, an agent lacks enough to invoke this safely on a repeat call, even though the fact definitions themselves are well covered.

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 0%, so the description must carry the parameter burden, and it largely does: hours_criterion is defined with its meaning and purpose (1,225-hour test for zelfstandigenaftrek), starter is mapped to startersaftrek entitlement, and wage_income is defined as gross employment wage with a stated use ('only to estimate how much tax to set aside'). Only the required `year` parameter is left undefined beyond the phrase 'a tax year', so one parameter remains unexplained.

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

Purpose4/5

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

The description names the resource precisely ('facts about a tax year that documents cannot show') and enumerates the three facts it holds (hours_criterion, starter, wage_income), so an agent immediately knows it stores manually-supplied year-level attributes rather than computed data. It stops short of stating the operation explicitly (that it writes/records these values) and does not name a distinguishing sibling, but the contrast with document-derived tools is implicit in 'documents cannot show'.

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

Usage Guidelines3/5

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

It supplies a strong data-sourcing rule ('Ask the owner; do not assume') and embeds why each fact matters (zelfstandigenaftrek, startersaftrek, tax set-aside), which tells the agent when the values are relevant. However, there is no explicit when-to-call trigger, no statement about whether repeated calls overwrite prior facts, and no mention of the sibling year_report that reads year data.

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