check_thresholdsChecks an annual income against the four statutory thresholds: VAT registration 2,000,000 CZK, immediate VAT registration 2,536,500 CZK, the 23% higher tax bracket, and the paušální daň eligibility ceiling. Reports approaching (90%), exceeded and remaining amounts.
| Name | Required | Description | Default |
|---|---|---|---|
| annualIncome | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
The readOnlyHint annotation already marks the tool as safe, and the description adds meaningful behavioral detail by specifying the output conditions: approaching (90%), exceeded, and remaining amounts. This enriches the agent's understanding without contradicting the annotation.
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?
Two concise sentences front-load the core action and then list the four thresholds and output behavior. There is no redundant or irrelevant text; every piece of information earns its place.
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 tool with a single numeric input and no output schema, the description fully covers both input meaning and result categories (approaching, exceeded, remaining). An agent has enough information to invoke the tool and interpret its returned values.
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?
The sole parameter annualIncome has no schema description, but the description clarifies it as an annual income amount and gives all thresholds in CZK, strongly implying the currency unit. This compensates for the 0% schema coverage, though it could be even more explicit.
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 uses a specific verb ('Checks') and names the exact resource: an annual income against four enumerated statutory thresholds (VAT, higher tax bracket, flat tax ceiling). This clearly distinguishes it from sibling tools like check_flat_tax_eligibility and compare_regimes.
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 intended use is clear: feed an annual income to detect threshold proximity and exceedance. It does not explicitly mention exclusions or alternative tools, but the tight scope and threshold details imply the correct usage context.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Add one secure layer between your agents and this server.
Most tools have clear distinct purposes, but calc_set_aside overlaps with compute_year (both compute safe-to-spend) and the flat-tax tools (check_flat_tax_eligibility, get_flat_tax_band, calc_flat_tax_settlement) could be confused without careful reading. Overall, descriptions are detailed enough to resolve ambiguity.
Nearly all tools follow a verb_noun pattern, but 'czech_working_days' is a noun phrase and the verbs vary (calc, compute, check, compare, convert, estimate, get). The use of both 'calc' and 'compute' for calculations is a minor inconsistency, but the pattern is still readable and predictable.
14 tools is well within the ideal range for a complex tax domain. Each tool addresses a distinct aspect (calculations, eligibility, deadlines, penalties, rules, currency, working days) and none seems redundant, making the count appropriate.
The tool surface covers the main OSVČ tax lifecycle: income tax, social/health insurance, flat tax, VAT thresholds, deadlines, penalties, and working days. A notable gap is the absence of a dedicated advance-payment (zálohy) calculation tool, though compute_year and get_rule_source can partially address this.