withholding-tax-calcAuto 10.21%/20.42% rate selection with reverse calculation.
| Name | Required | Description | Default |
|---|---|---|---|
| amount | Yes | Payment amount in JPY | |
| taxRate | No | Consumption tax rate (10 or 8) | |
| incomeType | No | Income type | freelance |
| taxHandling | No | Tax handling (exclusive=税抜, inclusive=税込) | exclusive |
| calcDirection | No | Calculation direction | gross-to-net |
Changes observed during successful MCP inspections. Dates show when Glama detected each change.
Input schema / $schemaAdded value: +"http://json-schema.org/draft-07/schema#"Input schema / properties / amountAdded value: +{
+ "description": "Payment amount in JPY",
+ "minimum": 0,
+ "type": "number"
+}Input schema / properties / calcDirectionAdded value: +{
+ "default": "gross-to-net",
+ "description": "Calculation direction",
+ "enum": [
+ "gross-to-net",
+ "net-to-gross"
+ ],
+ "type": "string"
+}Input schema / properties / incomeTypeAdded value: +{
+ "default": "freelance",
+ "description": "Income type",
+ "enum": [
+ "freelance",
+ "lawyer",
+ "performer",
+ "other"
+ ],
+ "type": "string"
+}Input schema / properties / taxHandlingAdded value: +{
+ "default": "exclusive",
+ "description": "Tax handling (exclusive=税抜, inclusive=税込)",
+ "enum": [
+ "exclusive",
+ "inclusive"
+ ],
+ "type": "string"
+}Input schema / properties / taxRateAdded value: +{
+ "anyOf": [
+ {
+ "const": 10,
+ "type": "number"
+ },
+ {
+ "const": 8,
+ "type": "number"
+ }
+ ],
+ "default": 10,
+ "description": "Consumption tax rate (10 or 8)"
+}Input schema / requiredAdded value: +[
+ "amount"
+]Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description discloses the essential behaviors: automatic rate selection (10.21%/20.42%) and reverse calculation. However, it does not explain the selection criteria (e.g., based on incomeType) or the output format, which are crucial for correct invocation.
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?
The description is one short, front-loaded sentence with no filler. It packs key differentiators (auto rate selection, reverse calculation) compactly.
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?
The tool has 5 parameters and complex tax logic (withholding + consumption tax, forward/reverse directions). The one-line description omits critical context: how the 10.21%/20.42% rates are chosen, what taxHandling and calcDirection do, and what the output represents. Without annotations or an output schema, this is insufficient for a financial calculation 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 covers all parameters with descriptions and enums, so baseline is 3. The description adds the 10.21%/20.42% rates but does not explicitly map them to parameters (e.g., incomeType), leaving a small gap between the described behavior and the schema's fields.
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 specifies the core function (withholding tax calculation) with distinctive behaviors: automatic 10.21%/20.42% rate selection and reverse calculation. This clearly separates it from sibling tax calculators like freelance-tax-calc or resident-tax-calc, though it does not explicitly state 'calculates withholding tax'.
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?
No guidance is given on when to use this tool versus alternative tax calculators. The description does not mention scenarios, prerequisites, or any exclusions, leaving the agent without context for selection.
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.
Multiple tools have overlapping purposes, such as bg-remover, bg-remover-pro, pro-matting, and takumi all performing background removal, and upscaler/upscaler-pro being redundant. With 202 tools, an agent may easily select the wrong one despite detailed descriptions.
Most tools use a consistent kebab-case format with descriptive names like pdf-compress, image-resizer, and tax-return-calc. Exceptions like 'takumi', 'pro-matting', and '-pro' suffixes (bg-remover-pro, upscaler-pro) are minor deviations relative to the total.
202 tools is an extreme mismatch for an MCP server, far exceeding the typical 3-15 well-scoped range. The sheer volume makes it unwieldy for an agent to efficiently navigate and select the right tool.
The tool set provides extensive coverage across many domains, including PDF operations (20+ tools), image editing, financial calculations, e-commerce fee estimation, and YouTube utilities. Minor gaps exist in cross-tool integration, but the breadth is highly comprehensive for the apparent purpose.