Skip to main content
Glama

TracePass DPP Compliance Assistant

Create a draft passport

create_draft_passport

Creates a draft passport in the user's own TracePass account from facts they stated. Use it whenever the user asks to create a passport, including "create and publish": create the draft, then say that publishing is done by the user in TracePass. It never publishes. If the result asks for an identifier, ask the user; never invent one. Use only what this tool returns: add no facts, dates or articles of your own, not even today's date. Keep every citation and the disclaimer line, and any "Planned, not law yet" or "being re-checked" label. For inScope no, never say "not yet" or "yet"; for pending, name the planned act from data.planned. Phrase answers about the product type, never as personal duties ("you must"). Never rank or recommend vendors. Never call this advice or yourself a consultant. If the result is not_covered, say so and point to the article given.

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": {
      "category": "<category>",
      "productName": "<productName>"
    },
    "name": "create_draft_passport"
  }
}

Input Schema

NameRequiredDescriptionDefault
gtinNoThe product's GTIN (barcode number, 8–14 digits). Required for most passport types. If missing, the tool will ask the user for it.
subTypeNoBattery only: EV, LMT or industrial_gt_2kwh. Used to count the required fields for that battery type; ask the user rather than guess.
categoryYesProduct category key, one of the listed values. Map the user's product to the closest key (paint → paints-coatings, an e-bike battery → battery). Never pass the user's own words. If none fits, there is no passport template for it: say so instead of calling.
productNameYesThe product's name.
serialNumberNoThe specific unit's serial number, if the passport is per-unit.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed3 schema fields changed
    • changedInput schema / properties / category / description
      Previous value: -"Product category, e.g. battery, textile."New value: +"Product category key, one of the listed values. Map the user's product to the closest key (paint → paints-coatings, an e-bike battery → battery). Never pass the user's own words. If none fits, there is no passport template for it: say so instead of calling."
    • addedInput schema / properties / category / enum
      Added value: +[
      +  "battery",
      +  "construction",
      +  "detergents",
      +  "electronics",
      +  "fmcg",
      +  "furniture",
      +  "jewelry",
      +  "packaging",
      +  "paints-coatings",
      +  "steel",
      +  "textile",
      +  "toys",
      +  "tyres"
      +]
    • removedInput schema / properties / category / maxLength
      Removed value: -100
  2. First observed

TDQS

A4.3/5.0
Behavior4/5

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

Annotations declare a non-read-only, non-destructive, non-idempotent write; the description goes well beyond that by disclosing that the call only creates a draft, that identifiers must never be invented, and how labels such as 'Planned, not law yet', 'being re-checked', and not_covered must be surfaced. The main undisclosed behavior is repeat-call semantics — with idempotentHint=false, it is not said whether calling twice yields two drafts — and it never describes what the returned draft contains. Strong coverage, one real gap.

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?

Purpose and the create-vs-publish boundary are front-loaded in the first two sentences, and the remaining constraints are each substantive rather than filler. The tail is a dense run of unpunctuated imperatives ('Never rank... Never call this advice...') that is harder to parse than the opening and could be grouped as an output-rules block.

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 carries the return contract and does so in useful detail — inScope no, pending/planned act, and not_covered outcomes are all described. What is missing for a write tool of this complexity is any statement about the created draft's identity (does it return an id or URL?) and duplicate-call behavior, which matters given non-idempotency.

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 category mapping, GTIN requirements, subType values and serialNumber meaning are already fully documented in structured fields. The description adds only a light behavioral overlay ('from facts they stated', 'If the result asks for an identifier, ask the user; never invent one'), which reinforces rather than extends the schema. Baseline 3 applies.

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 gives a specific verb and resource ('Creates a draft passport') and immediately bounds it with scope ('in the user's own TracePass account', 'from facts they stated'). It also explicitly differentiates itself from publishing ('It never publishes'), so an agent knows this tool cannot complete a publish request on its own.

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 trigger condition plainly ('Use it whenever the user asks to create a passport'), covers an ambiguous case ('including "create and publish"'), and gives the follow-up behavior that resolves it (create the draft, then tell the user publishing happens in TracePass). It also names a case where the tool must not be used effectively by pointing to the category enum's 'no template fits' path.

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.