extract

Jp Consumption Tax

jp_consumption_tax

Idempotent

Consumption tax: per-rate invoice rounding, qualified-invoice validation, simplified taxation, 20% special. $0.01/call. Deterministic, cites primary sources; errors and unverified rules are never billed.

Input Schema

TableJSON Schema

Name	Required	Description
`mode`	Yes	One of: invoice_totals, validate_invoice, simplified, two_percent
`as_of`	No	Calculation reference date YYYY-MM-DD (default today); selects the rules version
`lines`	No	Invoice lines [{amount_yen, qty, rate_key: standard\|reduced}]
`category`	No	Simplified-taxation business class 1-6
`document`	No	Qualified-invoice fields to validate (registration_number etc.)
`x_payment`	No	Optional: base64 X-PAYMENT header value (x402 exact scheme, USDC on Base mainnet). Omit it to receive the payment requirements (accepts[] + docs) for this call without being charged.
`taxable_period_end`	No	Taxable period last day YYYY-MM-DD (two_percent)
`taxable_period_start`	No	Taxable period first day YYYY-MM-DD (two_percent)
`taxable_sales_excl_yen`	No	Taxable sales excluding tax, in yen

Schema Changelog

Changes observed during successful MCP inspections.

Changed5 schema fields changedSep 27, 2026

addedInput schema / properties / as_of / format
```
Added value: +"date"
```

changedInput schema / properties / mode / description

Previous value: -"Extraction mode: auto (fast with rendered fallback), fast, heavy"New value: +"One of: invoice_totals, validate_invoice, simplified, two_percent"

addedInput schema / properties / mode / enum

Added value: +[
+  "invoice_totals",
+  "validate_invoice",
+  "simplified",
+  "two_percent"
+]

addedInput schema / properties / taxable_period_end / format
```
Added value: +"date"
```
addedInput schema / properties / taxable_period_start / format
```
Added value: +"date"
```

Changed8 schema fields changedSep 27, 2026

addedInput schema / properties / as_of / description

Added value: +"Calculation reference date YYYY-MM-DD (default today); selects the rules version"

addedInput schema / properties / category / description

Added value: +"Simplified-taxation business class 1-6"

addedInput schema / properties / document / description

Added value: +"Qualified-invoice fields to validate (registration_number etc.)"

addedInput schema / properties / lines / description

Added value: +"Invoice lines [{amount_yen, qty, rate_key: standard|reduced}]"

addedInput schema / properties / mode / description

Added value: +"Extraction mode: auto (fast with rendered fallback), fast, heavy"

addedInput schema / properties / taxable_period_end / description

Added value: +"Taxable period last day YYYY-MM-DD (two_percent)"

addedInput schema / properties / taxable_period_start / description

Added value: +"Taxable period first day YYYY-MM-DD (two_percent)"

addedInput schema / properties / taxable_sales_excl_yen / description
```
Added value: +"Taxable sales excluding tax, in yen"
```

Changed2 schema fields changedSep 26, 2026
- addedInput schema / properties / taxable_period_end
```
Added value: +{
+  "type": "string"
+}
```
- addedInput schema / properties / taxable_period_start
```
Added value: +{
+  "type": "string"
+}
```
AddedAug 19, 2026

TDQS

A3.5/5.0

Behavior4/5

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

Beyond the annotations, the description discloses meaningful behavior: it costs $0.01/call, is deterministic, cites primary sources, and never bills for errors or unverified rules. This adds practical operational context that annotations do not provide, while remaining consistent with the idempotentHint and openWorldHint annotations.

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?

The description is two sentences with no filler. It front-loads the tool's scope and immediately follows with pricing and reliability guarantees, every clause earning its place.

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?

For a tool with nine parameters, nested objects, multiple modes, and no output schema, the description gives solid high-level orientation but leaves mode-to-parameter mapping and return behavior to the schema. It is adequate but not fully complete for an agent deciding how to construct a correct call across all four modes.

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

Parameters3/5

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

Schema description coverage is 100%, so the schema itself documents each parameter. The description adds high-level context by naming the four modes and some tax-domain concepts, but it does not explain how parameters combine per mode or add meaning beyond the schema descriptions.

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 ('Consumption tax') and enumerates four specific capabilities: per-rate invoice rounding, qualified-invoice validation, simplified taxation, and 20% special. It does not use an explicit verb like 'calculates' or 'validates', but the capability list makes the tool's purpose clear and distinguishes it from sibling JP tax tools.

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

Usage Guidelines2/5

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

The description gives no explicit guidance on when to use this tool versus alternatives such as jp_crypto_tax or jp_retirement_tax, nor does it state when not to use it. Usage is only implied by the topic and mode names, so the agent must infer the appropriate selection context.

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

All extract tools Inspect

Try in Browser

Let your AI agent see the webWeb-to-screenshot MCP for Claude, Cursor and Codex. No cookie banners. Free to start.snap-render.comAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources

Need Help?