Skip to main content
Glama
Sign In
jp-number-grounding

jp-number-grounding

by japan-ai-tools
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Python
Remote

Check that numbers, amounts, dates and times in a Japanese summary appear in its source

jp_number_grounding_check
Read-onlyIdempotent

Verify numbers, dates, amounts, and times in a Japanese summary against the source, normalizing kanji numerals, eras, and times. Returns per-fact supported, approximate, mismatched, or unsupported.

Instructions

Before you send a summary, meeting minutes (議事録), report or answer written from a Japanese source, pass both texts here. Every number, money amount, percentage, count, date and time in the summary is normalized (三千五百万円 = 3,500万円 = 35,000,000円, 令和7年 = 2025年, R7.4.1 = 2025/4/1, 午後2時 = 14:00, 1割5分 = 15%, 12名 = 12人) and looked up in the source. Returns ok, problems, counts and per-fact status: supported, approx_supported (marked 約/程度 and within tolerance), year_unverified, unit_unverified, unit_mismatch (30人 vs 30件), unsupported (not in the source: often an invented deadline or a wrong figure). Also flags a weekday that does not match its date (W_WEEKDAY_MISMATCH). Deterministic, offline. It checks presence of values, not meaning. 要約の数字・日付・金額が原文にあるかを確かめる。

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": {
      "source": "<source>",
      "summary": "<summary>"
    },
    "name": "jp_number_grounding_check"
  }
}

Input Schema

NameRequiredDescriptionDefault
sourceYesOriginal text: transcript, document, email
summaryYesText written from the source (by an AI or a person)
toleranceNoRelative tolerance for values marked approximate (約). Default 0.1

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A4.3/5.0
Behavior5/5

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

Goes well beyond the annotations: it discloses normalization rules with worked examples (三千五百万円 = 35,000,000円, 令和7年 = 2025年, 午後2時 = 14:00), the full set of per-fact statuses including approx_supported, unit_mismatch and unsupported, the W_WEEKDAY_MISMATCH flag, and that it is deterministic and offline. Annotations already declare read-only/idempotent, and nothing here contradicts them.

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?

Front-loaded with the trigger, then normalization, then return shape, then limitations — a sensible order with no filler. The trailing Japanese sentence duplicates the purpose for bilingual use, which is mild redundancy rather than waste.

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

Completeness5/5

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 compensates by naming the returned fields (ok, problems, counts, per-fact status) and enumerating the possible statuses. For a two-text comparison tool with three parameters, an agent has everything needed to call and interpret it.

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 100%, so the baseline would be 3, but the description earns extra credit by tying the approximate-value status to tolerance semantics ('approx_supported (marked 約/程度 and within tolerance)'), giving meaning to the tolerance parameter beyond its schema text. Source vs summary roles are also reinforced by the 'pass both texts' phrasing.

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?

States a specific verb and resource: verify that numbers, amounts, dates and times in a Japanese summary appear in its source, with a concrete call pattern ('pass both texts here'). It is clearly distinguishable from a single-text number extractor, though it never names the sibling jp_number_extract, so an agent must infer the split.

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?

Gives an explicit trigger ('Before you send a summary, meeting minutes, report or answer written from a Japanese source') and a scope boundary ('checks presence of values, not meaning'). It does not name an alternative tool or say when not to use this one, so routing versus jp_number_extract is left implicit.

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

Deploy Server

Other Tools