Aurelmark

Check EUDR product scope

eudr_check_scope

Read-onlyIdempotent

Returns whether one CN/HS/TARIC code is covered by the EU Deforestation Regulation (EUDR) Annex I, with the matching product lines and official sources. Use it to check a single code; use eudr_list_products to browse the whole Annex I catalogue, and cbam_get_default_values for CBAM, a different law. Input: cn (required, code or prefix, 2 to 10 digits, spaces and dots ignored, e.g. 0901 for coffee). Output: verdict (yes, partly, some_codes_below, applies_later or no), in_scope, meaning, matches[], upcoming[], removed products, applies_from, sources and verified. Annex I as amended by Delegated Regulation (EU) 2026/2102: cattle hides, skins and leather (4101, 4104, 4107) are removed (verdict no, with removed set); products it adds, such as soluble coffee 2101 11 00, apply only from 2027-12-30 and give applies_later with upcoming[]. some_codes_below means a longer code is needed; partly means an ex line where only the described goods are covered. Bundled from the official acts and reviewed as of verified; this is scope information, not a due-diligence statement. Terms: read-only; MCP calls are never charged. Without a key, metered routes give 10 successful answers a day free, as short samples (up to 3 records, without file proof, history or paging cursor) where a paid HTTP address exists (unmetered routes are unlimited); errors do not count. On the paid HTTP routes, errors are free, and so are empty answers except a sanctions name search with no match when every loaded list it checks is fresh (lists not loaded yet are named in the answer). An optional API key keeps its prepaid-credit policy. When the free answers run out, the error names the HTTP alternative.

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": {
      "cn": "<cn>"
    },
    "name": "eudr_check_scope"
  }
}

Input Schema

Name	Required	Description	Default
`cn`	Yes	CN/HS/TARIC code or prefix, 2 to 10 digits after removing spaces and dots, e.g. 0901

Schema Changelog

Changes observed during successful MCP inspections.

AddedNov 3, 2026

TDQS

A4.3/5.0

Behavior4/5

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

Annotations already cover read-only, idempotent and non-destructive semantics, yet the description adds substantial context: the full verdict taxonomy and what each means, the 2026/2102 amendment behaviour (4101/4104/4107 removed -> 'no' with a removed set; added products apply only from 2027-12-30 -> 'applies_later' with upcoming[]), and metering/rate-limit rules including what counts against the free quota. The one deduction is that the metering block is wordy and partly generic policy text rather than tool-specific behaviour.

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 purpose, verdict vocabulary and amendment caveats are front-loaded and genuinely earn their place, since there is no output schema. However, roughly the back half is a dense, repetitive free-tier/metering/API-key paragraph that could be compressed to one sentence ('free tier: 10 metered answers/day, errors free'), and it dilutes the operational content an agent needs at call time.

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?

With no output schema, the description carries the return-shape burden and does so: it enumerates verdict values (yes, partly, some_codes_below, applies_later, no) with their meanings and lists the fields returned (in_scope, meaning, matches[], upcoming[], removed set, applies_from, sources, verified). It also sets expectations that this is scope information, not a due-diligence statement, which prevents misuse.

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 coverage is 100% and the schema already documents 'cn' as a 2-to-10-digit code with spaces and dots removed, including the 0901 example. The description repeats the same rules ('2 to 10 digits, spaces and dots ignored, e.g. 0901 for coffee') and adds only the semantic gloss that 0901 means coffee, which is marginal. Baseline 3 applies when the schema does the heavy lifting.

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 names a specific verb and resource ('Returns whether one CN/HS/TARIC code is covered by the EUDR Annex I') plus what comes back (matching product lines and official sources). It explicitly contrasts itself with eudr_list_products (browse the catalogue) and cbam_get_default_values (a different law), so an agent can select it without opening any schema.

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

Usage Guidelines5/5

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

It states the use case directly ('Use it to check a single code') and names both the same-domain alternative and the confusable cross-domain tool, with the condition that separates them. Later it also clarifies the single-code scope via the 'some_codes_below' and 'partly' verdict explanations, telling the agent when a returned answer means 'ask again with a longer code' rather than 'not covered'.

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

All Aurelmark 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.