Skip to main content
Glama

search_operators_near_itinerary

Read-onlyIdempotent

Find operators near EVERY stop of a curated itinerary, in one call.

Use this after search_itineraries instead of calling search_operators once
per stop: it reads the route's ordered, geocoded stops and returns what is
near each one in a single round trip, with a rural-correct radius so route
operators are not missed. The itinerary stays operator-agnostic — this reads
the route and finds operators near it; it never embeds operators in the
itinerary itself.

Each stop carries TWO separate arrays, and they are not interchangeable:

- ``operators`` — connected Sóley operators. Bookable through this server:
  continue with get_services, check_availability, create_booking.
- ``registry_listings`` — entries from Iceland's public licensed-operator
  registers. Informational only. They carry ``bookable: false``, and must
  never be presented as available to reserve through Sóley. Their returned
  ``result_kinds.registry_listings`` guidance carries the canonical direct-
  contact instruction. Each entry states
  the basis of its coordinates in ``location_note``: a licensed address, an
  approximate postcode centroid, or an owner-supplied point. For day-tour
  operators and travel agencies the registered address is an office, not a
  departure point — repeat that caveat rather than implying a meeting place.

Describe results by capability, never by membership. Present the
``registry_presentation.attribution`` string verbatim when you use register
entries. ``registry_total_count`` per stop is the unclipped match count —
when it exceeds what is returned, call search_licensed_operators with that
stop's place or region for the full ranked list.

Operators and listings may appear under more than one nearby stop.

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": {
      "itinerary_id": "<itinerary_id>"
    },
    "name": "search_operators_near_itinerary"
  }
}

Input Schema

NameRequiredDescriptionDefault
radius_kmNoOptional search radius per stop, in km. Leave empty to use the rural-correct default (Iceland's route stops are tens of km apart).
itinerary_idYesID of an enabled itinerary (the 'id' returned by search_itineraries). The tool reads that route's ordered stops and finds operators near each.
service_typeNoOptional: only return operators offering this service category.
max_price_iskNoOptional maximum price filter in ISK.
min_price_iskNoOptional minimum price filter in ISK.

Output Schema

NameRequiredDescriptionDefault

No arguments

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.6/5.0
Behavior5/5

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

Annotations already declare readOnly/idempotent/non-destructive, and the description goes well beyond them: it explains the rural-correct default radius rationale, that the itinerary stays operator-agnostic, and that operators and listings may repeat across stops. It also discloses the critical behavioral distinction between the two arrays, that registry entries are bookable:false and informational only, the location_note basis of coordinates, the office-vs-departure-point caveat, and the requirement to reproduce the attribution string verbatim.

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 routing guidance are front-loaded, and the bulleted split of operators vs registry_listings is easy to scan. It loses a point for mild repetition — the operator-agnostic idea is restated in the same sentence ('this reads the route and finds operators near it; it never embeds operators in the itinerary itself'), and the caveat paragraph is dense.

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 read-only aggregation tool with an output schema and full annotation coverage, the description supplies everything the agent still needs: where it sits in the itinerary workflow, how to handle each result array downstream (get_services, check_availability, create_booking), and the presentation constraints on registry data.

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 carries the meaning of all five parameters. The description reinforces the radius default ('rural-correct radius') but says nothing about service_type, min_price_isk, or max_price_isk semantics beyond what the schema states, so it adds only marginal value here.

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 first line states a specific verb and resource with scope: 'Find operators near EVERY stop of a curated itinerary, in one call.' It distinguishes itself from the sibling pattern of calling search_operators per stop and later names search_licensed_operators as the escalation path, so an agent can place it without opening a schema.

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?

Explicit sequencing guidance: 'Use this after search_itineraries instead of calling search_operators once per stop,' which names both the prerequisite and the alternative it replaces. It also gives a concrete condition for switching tools — when registry_total_count exceeds what is returned, call search_licensed_operators for that stop's place or region.

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