Skip to main content
Glama

GPFR: register a person who said yes

gpfr_register

Registers a person in GPFR after they said yes to the consent sentence from gpfr_info, shown word for word. It sends one confirmation email and the registration stays pending until they click its link. At most 3 emails a day per address.

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": {
      "email": "<email>",
      "name": "<name>",
      "date_of_birth": "<date_of_birth>",
      "periods": "<periods>",
      "consent": "<consent>"
    },
    "name": "gpfr_register"
  }
}

Input Schema

NameRequiredDescriptionDefault
nameYesThe person's full name, as an employer or fund would hold it. Hashed on receipt.
emailYesThe person's email address. We send one confirmation email to it.
consentYesRequired. The yes the person gave to the gpfr_info consent sentence.
periodsYesWhere the person worked: country, years, optional employer and fund.
languageNoOptional. Default en. GPFR is live in 24 languages: en, ar, da, de, es, fa, fr, hi, id, it, ja, ko, nb, nl, pl, pt, pt-BR, ro, ru, sv, th, tl, tr, zh. bg, uk, vi are answered in English.
date_of_birthYesYYYY-MM-DD. Hashed on receipt.
earlier_namesNoOptional earlier full names. Hashed on receipt.
national_numberNoOptional national number and its issuing country.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed10 schema fields changed
    • changedInput schema / properties / consent / description
      Previous value: -"Required. The yes the person gave after you showed them the gpfr_info consent sentence in their language."New value: +"Required. The yes the person gave to the gpfr_info consent sentence."
    • changedInput schema / properties / consent / properties / consent_text_version / description
      Previous value: -"The consent.version from gpfr_info for the sentence you showed, exactly as returned."New value: +"The consent.version from gpfr_info, exactly as returned."
    • changedInput schema / properties / consent / properties / person_said_yes / description
      Previous value: -"true only when the person said yes to the sentence you showed."New value: +"true only when the person said yes to the sentence shown."
    • changedInput schema / properties / earlier_names / description
      Previous value: -"Optional earlier full names (maiden or former). Hashed on receipt."New value: +"Optional earlier full names. Hashed on receipt."
    • changedInput schema / properties / email / description
      Previous value: -"The person's email address. We send one email to confirm it; nothing happens until they click it."New value: +"The person's email address. We send one confirmation email to it."
    • changedInput schema / properties / language / description
      Previous value: -"Optional. ISO 639-1 code for our sentences and the consent text: en, ar, da, de, es, fa, fr, hi, id, it, ja, ko, nb, nl, pl, pt, pt-BR, ro, ru, sv, th, tl, tr, zh. Default en. Any other language is answered in English, with languageNote saying so."New value: +"Optional. Default en. GPFR is live in 24 languages: en, ar, da, de, es, fa, fr, hi, id, it, ja, ko, nb, nl, pl, pt, pt-BR, ro, ru, sv, th, tl, tr, zh. bg, uk, vi are answered in English."
    • changedInput schema / properties / national_number / description
      Previous value: -"Optional national number and its issuing country. Hashed on receipt."New value: +"Optional national number and its issuing country."
    • changedInput schema / properties / periods / items / properties / country / description
      Previous value: -"ISO 3166-1 alpha-2 code of a country GPFR covers."New value: +"A country: English or native name, alias or ISO code, for example NL or Netherlands."
    • changedInput schema / properties / periods / items / properties / employer / description
      Previous value: -"The employer's name, optional. Checked against the country, then hashed; never stored as text."New value: +"Employer name as the person knows it. Optional."
    • changedOutput schema / (root)
      Previous value: -{
      -  "additionalProperties": false,
      -  "properties": {
      -    "language": {
      -      "type": "string"
      -    },
      -    "languageNote": {
      -      "description": "Present only when the language asked for is not a GPFR language: why the answer and the consent text are in English.",
      -      "type": "string"
      -    },
      -    "note": {
      -      "type": "string"
      -    },
      -    "reference": {
      -      "description": "R-XXXX-XXXX-XXXX, for gpfr_status. Not personal data.",
      -      "type": "string"
      -    },
      -    "status": {
      -      "enum": [
      -        "pending_email_confirmation"
      -      ],
      -      "type": "string"
      -    }
      -  },
      -  "required": [
      -    "status",
      -    "reference",
      -    "note"
      -  ],
      -  "type": "object"
      -}New value: +null
  2. Added

TDQS

A4.4/5.0
Behavior5/5

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

Goes well beyond the annotations (readOnly=false, openWorld=true, idempotent=false, destructive=false) by disclosing the side effect (one confirmation email), the resulting state transition (registration stays pending until the link is clicked), and a rate limit (max 3 emails/day per address). These are exactly the traits an agent needs to reason about a non-idempotent mutation.

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

Conciseness5/5

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

Three tight sentences, front-loaded with what the tool does, then the confirmation-email side effect and rate limit. No filler; each sentence carries distinct information.

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?

For a mutation tool with nested objects, no output schema, and only four annotations, the description covers the precondition, side effect, state outcome, and rate limit. It does not describe the response payload or failure behavior, which is a minor gap given there is no output schema to lean on.

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 nested consent, periods, language, and hashing details are already fully documented in the schema. The description adds only light framing around the consent sentence and confirmation email, so the 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?

States a specific verb and resource ('registers a person in GPFR') and anchors the workflow to the sibling gpfr_info ('after they said yes to the consent sentence from gpfr_info'), so an agent can tell this apart from gpfr_info/gpfr_status without opening the schema.

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 a clear precondition: call this only after the person said yes to the gpfr_info sentence 'shown word for word'. It does not name when-not-to-use or an explicit alternative tool, so it stops short of full routing guidance.

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.