Skip to main content
Glama

swiss-living-index

Which permit fits

which_permit
Read-onlyIdempotent

Which Swiss permit fits a person (the Swiss Living Index permit route finder as a tool): from nationality and plan (visit, work, commute from abroad, join family, study, retire, live without working, or already living here on a B permit) returns the permit (L, B, C, G or none), whether it is an entitlement or at the canton's discretion, the 2026 quota for non-EU work, every rule with its law article (AIG, VZAE, BüG) or SEM page, and for people already here the years until a C permit and naturalisation. Same logic as the page, checked by 45 test cases. Asylum statuses are out of scope. Information, not legal advice: the cantonal migration office decides.

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": {
      "nationality": "<nationality>",
      "plan": "<plan>"
    },
    "name": "which_permit"
  }
}

Input Schema

NameRequiredDescriptionDefault
ageNoAge in years, used for plan retire (e.g. 62).
planYesWhat the person wants to do in Switzerland: visit, work, commute (live abroad, work here), family (join family), study, retire, nonactive (live without working) or here (already living here).
qualifiedNowork, non-EU: manager, specialist or other qualified worker (default true)
job_lengthNowork: under 3 months, 3 to 12 months, a year or longer / open-ended (default ge12)
nationalityYesISO 3166 alpha-2 code (e.g. DE, PL, GB, US, IN) or a group: eu5, eu, uk, other
years_on_b_permitNohere: years on a B permit without interruption
ties_to_switzerlandNoretire: earlier long stays or close relatives in Switzerland
family_member_is_eu_eftaNofamily: that person is an EU/EFTA national (free movement rules, not covered)
family_member_in_switzerlandNofamily: status of the person in Switzerland

Output Schema

NameRequiredDescriptionDefault
attributionNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed4 schema fields changed
    • addedInput schema / additionalProperties
      Added value: +false
    • changedInput schema / properties / age / description
      Previous value: -"retire"New value: +"Age in years, used for plan retire (e.g. 62)."
    • addedInput schema / properties / plan / description
      Added value: +"What the person wants to do in Switzerland: visit, work, commute (live abroad, work here), family (join family), study, retire, nonactive (live without working) or here (already living here)."
    • changedOutput schema / (root)
      Previous value: -nullNew value: +{
      +  "properties": {
      +    "attribution": {
      +      "type": "string"
      +    }
      +  },
      +  "type": "object"
      +}
  2. Added

TDQS

A3.7/5.0
Behavior4/5

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

Annotations already cover read-only/idempotent/no side effects, so the description's added value is the scope boundary (asylum excluded) and the disclaimer that this is information, not legal advice, with the cantonal migration office deciding. That is meaningful context about reliability and limits that annotations cannot express.

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?

Front-loaded with the tool's purpose and output shape, and nearly every clause carries information (return payload, scope exclusion, disclaimer). The main flaw is that the whole specification is a single ~100-word run-on sentence with a parenthetical, which hurts scanability.

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 9-parameter decision engine with full schema coverage and an output schema, the description supplies the purpose, conditional context (B permit, retire, non-EU quota) and trust/disclaimer notes. It does not explain how conditional parameters interact (e.g. qualified/job_length only apply to non-EU work), but the schema largely carries that.

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 schema already documents all 9 parameters including enums and defaults. The description only restates the plan options and lightly hints which params matter (B-permit years for the 'here' route), adding little beyond the structured fields.

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?

States a concrete verb and resource ('which permit fits a person' -> returns the permit L/B/C/G/none), plus the exact output payload (entitlement vs discretion, 2026 quota, rule citations). It is clearly distinct from siblings like permit_types or work_permit_quotas, though no sibling is named explicitly.

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

Usage Guidelines3/5

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

Usage is implied by enumerating the input situation (nationality + plan such as visit/work/retire/here), and one exclusion is given ('Asylum statuses are out of scope'). However, it never says when to call this instead of permit_types, work_permit_quotas, naturalisation_timing, or family_reunification, which overlap with its outputs.

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