Skip to main content
Glama

Find company in Peppol e-invoicing network

find_peppol_participant
Read-onlyIdempotent

Looks up whether a company can receive e-invoices via Peppol. Search by VAT ID (the usual Peppol identifiers are derived automatically), by a known Peppol participant ID, or by company name. Returns two parts: the Peppol Directory (where listing is voluntary) and, for a VAT ID or participant ID, the Peppol network itself (SML and the provider's SMP), which also finds companies that are not listed in the directory. 'registered' with confirmed: true (the provider's SMP lists business documents) means reachable via Peppol, with the documents it receives; 'registered' without confirmed is only an SML entry and does not prove reachability. 'not registered' only covers the identifiers looked up; the company may use another one. A name search asks the directory only.

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "find_peppol_participant"
  }
}

Input Schema

NameRequiredDescriptionDefault
nameNoCompany name, if neither VAT ID nor participant ID is known.
vat_idNoThe company's VAT ID or Swiss UID.
countryNoOptional two-letter country code for a name search.
with_receiptNoOptional, default false. Set true only when the user asks for a signed receipt of this check for their files.
participant_idNoA known Peppol participant ID: four-digit scheme code, colon, identifier, e.g. 0208:0202239951.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed2 schema fields changed
    • changedInput schema / properties / name / description
      Previous value: -"Company name, if no VAT ID is known."New value: +"Company name, if neither VAT ID nor participant ID is known."
    • addedInput schema / properties / participant_id
      Added value: +{
      +  "description": "A known Peppol participant ID: four-digit scheme code, colon, identifier, e.g. 0208:0202239951.",
      +  "maxLength": 120,
      +  "type": "string"
      +}
  2. Changed2 schema fields changed
    • addedInput schema / additionalProperties
      Added value: +false
    • addedInput schema / properties / with_receipt
      Added value: +{
      +  "description": "Optional, default false. Set true only when the user asks for a signed receipt of this check for their files.",
      +  "type": "boolean"
      +}
  3. First observed

TDQS

A4.5/5.0
Behavior5/5

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

Annotations already declare readOnly, idempotent and non-destructive, yet the description adds genuine behavioral depth: two result sources, the voluntary nature of the directory, the SML/SMP distinction, and what 'confirmed: true' versus an unconfirmed SML entry actually proves. It also scopes the meaning of a negative result, warning that 'not registered' covers only the identifiers looked up.

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?

Dense but front-loaded: purpose first, then lookup modes, then result interpretation. Every sentence carries information, though the result-semantics block is a wall of clauses that could be broken into shorter statements for faster scanning.

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 must carry return-value meaning, and it does so well by defining the 'registered'/'not registered' outcomes and their evidentiary weight. It leaves the actual response shape (fields returned per source, error cases, rate limits) unspecified, which is the remaining gap for a five-parameter open-world lookup.

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 baseline is 3; the description still earns credit by explaining that Peppol identifiers are derived automatically from a VAT ID and that a name search is directory-only, which tells the agent how the parameters interact. It does not add syntax detail beyond the schema's participant ID example.

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?

States a specific verb and resource ('looks up whether a company can receive e-invoices via Peppol') and scopes it to the Peppol network, which separates it from siblings like find_swiss_company or check_vat_id. The three lookup paths (VAT ID, participant ID, name) are named up front.

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 clear selection guidance among the three identifier modes: VAT ID is 'the usual', participant ID when known, name only when neither is known. It also flags that a name search hits the directory only. What is missing is any comparison to sibling identity/VAT tools (e.g. check_vat_id), so an agent must infer the boundary.

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.

Resources