Taiwan Carbon Open Data (Unofficial)

Build GHG inventory summary

build_inventory

Read-onlyIdempotent

Calculate several activities and arrange the results as a greenhouse gas inventory: grouped into Scope 1 (direct), Scope 2 (purchased energy) and Scope 3 (other indirect), with a subtotal per scope, Scope 1 by gas, and a Scope 1+2 total. Subtotals and totals are withheld, with the reason, when items mix CO2 and CO2e, when an item could not be calculated, or when Scope 3 holds product carbon footprints that may overlap Scopes 1 and 2. The scope assignment is this service's default by factor type and can be overridden per item. Covers only the activities supplied; it is not a complete or verified inventory. 計算多筆活動並整理成溫室氣體盤查清冊的形式：分為範疇一（直接排放）、範疇二（能源間接）、範疇三（其他間接），提供各範疇小計、範疇一依氣體分列，以及範疇一加二的合計。項目混用 CO2 與 CO2e、有項目算不出來、或範疇三含可能與範疇一、二重疊的產品碳足跡時，不提供對應的小計或合計並說明原因。範疇分類是本服務依係數類型的預設，可逐筆覆寫。只涵蓋你提供的活動，不是完整或經查證的盤查。

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": {
      "items": "<items>"
    },
    "name": "build_inventory"
  }
}

Input Schema

Name	Required	Description	Default
`items`	Yes	要列入清冊的活動，最多 50 筆。
`inventory_year`	No	盤查年度（西元）。會套用到沒有自己指定 year 的項目，係數年度不符的項目會回報錯誤。

Schema Changelog

Changes observed during successful MCP inspections.

First observedNov 13, 2026

TDQS

A4.2/5.0

Behavior5/5

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

Beyond the read-only/idempotent annotations, it discloses a non-obvious behavioral rule: subtotals and totals are withheld, with a reason, when CO2 and CO2e are mixed, when an item fails to calculate, or when Scope 3 contains product carbon footprints overlapping Scopes 1–2. It also reveals that scope assignment is a service default by factor type and is overridable per item, plus an explicit accuracy caveat.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness3/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The inventory structure and withholding rules are front-loaded and well organized, but the entire description is duplicated verbatim in Chinese, roughly doubling length with no added information for an agent reading both. The English portion alone would be tight and effective.

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

Completeness4/5

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

With no output schema, the description usefully explains the shape of the result (per-scope subtotals, Scope 1 by gas, 1+2 total, suppressed values with reasons). Remaining gaps are minor, such as per-item error reporting and what a failed calculation returns, though the schema hints at the latter.

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 already documents items, scope override, quantity and factor inputs in detail. The description adds little parameter-level meaning beyond restating that scope assignment is a default by factor type and can be overridden per item, which the schema's scope property already conveys.

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

Purpose5/5

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

The opening sentence pairs a specific verb (calculate) with a specific artifact (a greenhouse gas inventory grouped into Scope 1/2/3 with subtotals, per-gas breakdown and a 1+2 total). That output shape separates it from single-activity calculators like calculate_emissions or calculate_batch, which do not produce a structured inventory.

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?

It sets clear context with 'Covers only the activities supplied; it is not a complete or verified inventory', which tells the agent when this result is and isn't sufficient. It never names an alternative tool or states an explicit exclusion ('do not use for X, use Y'), so it falls short of the top score.

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

All Taiwan Carbon Open Data (Unofficial) tools Inspect

Try in Browser

One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.