Skip to main content
Glama

TracePass DPP scope checker

tracepass_scope

Check what EU law says for a product type matching the facts given: whether it needs a Digital Product Passport, from when, at which level, under which act and article, and the duties of each role. Also reads the catalogue-wide scope report and triggers a refresh run.

HARD RULES — always apply to scope answers:

  • State what the law says for product types matching the given facts. Not legal advice; never write 'you must' — use product-type phrasing ('LMT batteries need a passport from 18 February 2027, Battery Regulation Art. 77(1)').

  • Cite the article given for every verdict and duty; a regulation without an article is not a citation. not_covered rests on no article: say our rules do not cover the product, name the nearest act given, never cite it as the basis.

  • A date with precision 'quarter', 'month' or 'year' is a plan, NEVER a deadline: write 'planned for Q2 2027 (planned, not law yet)', never 'from', 'by' or 'deadline'.

  • Relay not_covered and needs_input as results, never errors. needs_input = blocking questions remain — relay ask[] to the user before giving a verdict.

  • Items in an act's planned list are not law yet: label them 'Planned, not law yet' (labelText), with their wording.

  • data.inScope: yes = passport required; no = none required AND none planned (incl. ESPR-framework-only products, packaging): never say 'not yet' or 'yet'; pending = none today, a passport act is planned: name it from planned[]; depends = unanswered facts.

  • ruleStatus: 'needs_recheck': the law behind the act changed and our rules are being re-checked (since recheckSince); say so.

Actions (pass via action; {…} is the args object); values, caps and response shapes: resource tracepass://reference/scope.

  • check — { category?, facts?, role?, placedOnMarket?, lifecycleEvent?, contains?, productId?, passportId?, locale? }. Every plan; counts against the scope-answer cap (~100/day), not the v1 budget (429 scope_answer_cap). Unknown facts keys: 400. Omit role for all roles' duties.

  • catalogue_report — { classification?, category?, act?, changed?, q?, cursor?, limit? (≤500) }. One row per product. Growth plan or above; 403 plan_upgrade_required below it — tell the user this needs a plan upgrade, do not retry.

  • catalogue_run — {}. Start a refresh run (also nightly); poll with catalogue_run_status. Growth plan. 409 run_in_progress; 429 run_cooldown.

  • catalogue_run_status — { runId }. Growth plan.

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": {
      "action": "<action>"
    },
    "name": "tracepass_scope"
  }
}

Input Schema

NameRequiredDescriptionDefault
argsNo
actionYes

Output Schema

NameRequiredDescriptionDefault
idNo
pageNo
errorNo
itemsNo
limitNo
totalNo
resultNo
messageNo
totalPagesNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed27 schema fields changed
    • removedInput schema / properties / action / description
      Removed value: -"Which scope operation to run: check | catalogue_report | catalogue_run | catalogue_run_status."
    • removedInput schema / properties / args / description
      Removed value: -"Arguments for the chosen action; required fields depend on `action` (see above)."
    • changedInput schema / properties / args / properties / act / description
      Previous value: -"Filter catalogue_report by governing act (CELEX, e.g. 32023R1542)."New value: +"CELEX, e.g. 32023R1542."
    • changedInput schema / properties / args / properties / category / description
      Previous value: -"Product category for check (battery, textile, vehicles, other, …)."New value: +"Product category (values: tracepass://reference/scope)."
    • removedInput schema / properties / args / properties / changed / description
      Removed value: -"catalogue_report: true to return only rows changed since the last run."
    • removedInput schema / properties / args / properties / classification / description
      Removed value: -"Filter catalogue_report by classification: missing | draft_only | published_incomplete | published | not_required | open_questions | not_covered."
    • removedInput schema / properties / args / properties / contains / description
      Removed value: -"Component queries for check (max 5), e.g. a toy containing a battery."
    • removedInput schema / properties / args / properties / cursor / description
      Removed value: -"Pagination cursor (catalogue_report)."
    • changedInput schema / properties / args / properties / facts / description
      Previous value: -"Fact key→value map for check (e.g. { 'battery.use': 'ev' })."New value: +"Namespaced fact keys, e.g. { 'battery.use': 'ev' }."
    • removedInput schema / properties / args / properties / lifecycleEvent / description
      Removed value: -"Lifecycle event for check (e.g. end_of_life)."
    • removedInput schema / properties / args / properties / limit / description
      Removed value: -"Page size for catalogue_report, max 500."
    • removedInput schema / properties / args / properties / locale / description
      Removed value: -"Answer locale for check: en | bg | de | it."
    • changedInput schema / properties / args / properties / passportId / description
      Previous value: -"Passport id — adds saved passport facts to check."New value: +"Adds saved passport facts."
    • changedInput schema / properties / args / properties / placedOnMarket / description
      Previous value: -"Placing date for check: { date: YYYY[-MM[-DD]], precision?: day|month|year } or null."New value: +"{ date: YYYY[-MM[-DD]], precision?: day|month|year } or null."
    • changedInput schema / properties / args / properties / productId / description
      Previous value: -"Product id — adds saved product facts and passport data to check."New value: +"Adds saved product facts."
    • removedInput schema / properties / args / properties / q / description
      Removed value: -"catalogue_report: search by product name or GTIN."
    • changedInput schema / properties / args / properties / role / description
      Previous value: -"Role hint for check (e.g. manufacturer, importer, ownBrand)."New value: +"manufacturer | importer | distributor | authorised_representative | fulfilment_service_provider."
    • removedInput schema / properties / args / properties / runId / description
      Removed value: -"Run id to poll (catalogue_run_status)."
    • removedOutput schema / properties / error / description
      Removed value: -"Machine-readable error code, when the API rejected the request."
    • removedOutput schema / properties / id / description
      Removed value: -"The resource's TracePass id, when the response is a single entity."
    • removedOutput schema / properties / items / description
      Removed value: -"The page of results, when the action is a list."
    • removedOutput schema / properties / limit / description
      Removed value: -"Page size (list actions)."
    • removedOutput schema / properties / message / description
      Removed value: -"Human-readable error or status detail, when present."
    • removedOutput schema / properties / page / description
      Removed value: -"Current page number (list actions)."
    • removedOutput schema / properties / result / description
      Removed value: -"Wraps a non-object response body (e.g. a QR code string)."
    • removedOutput schema / properties / total / description
      Removed value: -"Total matching records across all pages (list actions)."
    • removedOutput schema / properties / totalPages / description
      Removed value: -"Total number of pages (list actions)."
  2. Changed10 schema fields changed
    • removedInput schema / properties / args / properties / lifecycleEvent / anyOf
      Removed value: -[
      -  {
      -    "type": "string"
      -  },
      -  {
      -    "type": "null"
      -  }
      -]
    • addedInput schema / properties / args / properties / lifecycleEvent / type
      Added value: +[
      +  "string",
      +  "null"
      +]
    • removedInput schema / properties / args / properties / passportId / anyOf
      Removed value: -[
      -  {
      -    "type": "string"
      -  },
      -  {
      -    "type": "null"
      -  }
      -]
    • addedInput schema / properties / args / properties / passportId / type
      Added value: +[
      +  "string",
      +  "null"
      +]
    • removedInput schema / properties / args / properties / productId / anyOf
      Removed value: -[
      -  {
      -    "type": "string"
      -  },
      -  {
      -    "type": "null"
      -  }
      -]
    • addedInput schema / properties / args / properties / productId / type
      Added value: +[
      +  "string",
      +  "null"
      +]
    • removedOutput schema / properties / error / anyOf
      Removed value: -[
      -  {
      -    "type": "string"
      -  },
      -  {
      -    "type": "null"
      -  }
      -]
    • addedOutput schema / properties / error / type
      Added value: +[
      +  "string",
      +  "null"
      +]
    • removedOutput schema / properties / message / anyOf
      Removed value: -[
      -  {
      -    "type": "string"
      -  },
      -  {
      -    "type": "null"
      -  }
      -]
    • addedOutput schema / properties / message / type
      Added value: +[
      +  "string",
      +  "null"
      +]
  3. Added

TDQS

A4.3/5.0
Behavior5/5

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

Well beyond the annotations, the description discloses concrete operating behavior: a scope-answer cap (~100/day) with 429 `scope_answer_cap`, plan gating with 403 `plan_upgrade_required` and an explicit 'do not retry' instruction, 409 `run_in_progress` and 429 `run_cooldown` for the run action, 400 on unknown `facts` keys, and the fact that a refresh also runs nightly. It also explains how to interpret `data.inScope` values and `ruleStatus: 'needs_recheck'`, which is real semantic behavior the agent cannot infer elsewhere.

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?

Structure is strong: purpose first, then a bulleted HARD RULES block, then a per-action list keyed by the `action` values, so the reader can jump straight to the relevant line. It is long and the legal-phrasing rules are dense output-style instructions rather than invocation guidance, but each rule addresses a real failure mode (calling a planned date a deadline, citing an act without an article, treating `needs_input` as an error).

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?

For a four-action, nested-argument, legally sensitive tool, the description covers what an agent needs to invoke it correctly: action routing, plan prerequisites, rate caps, retry/no-retry signals, and how to relay each result state. An output schema exists, so return shapes need not be explained, and the definition correctly points to `tracepass://reference/scope` for values and caps instead of duplicating them.

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?

The schema's top-level `args` object carries almost no description, so the description does the work: it lists the accepted keys per action, gives `limit` (≤500), flags `changed?`/`cursor?` for paging, and states that unknown `facts` keys return 400 and that omitting `role` yields all roles. It defers enum values and response shapes to `tracepass://reference/scope` rather than restating them, which is a reasonable pointer but leaves some parameters (e.g. `classification`, `lifecycleEvent`) without added meaning here.

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 first sentence states a specific verb and resource: check what EU law says for a product type — whether a Digital Product Passport is needed, from when, at which level, under which act/article, plus per-role duties — and it separately names the catalogue report read and the refresh trigger. The four `action` values are enumerated with one-line scopes, so an agent can tell what the tool does. It never names a sibling (e.g. tracepass_passports) to sharpen the boundary, which is the only thing keeping it off a 5.

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?

Selection among the tool's own actions is explicit: `check` for a scope verdict, `catalogue_report` for one-row-per-product data, `catalogue_run` to start a refresh and `catalogue_run_status` to poll it. It also states the preconditions that change behavior — Growth plan required for the catalogue actions, 'do not retry' on 403, omit `role` to get all roles' duties. It gives no guidance on when to prefer this tool over its sibling passport/product tools, so the guidance is strong internally but not externally routed.

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

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.