Skip to main content
Glama

Search stays

search_stays
Read-onlyIdempotent

Search Guestit apartments and holiday homes in Sweden for a trip using a location_id from resolve_destination. Use the traveler’s dates and guest count; ask for them before quoting a stay total. Refine by resending the full filter set. Each stay is a short card; read house rules and the cancellation policy with stay_details or compare_stays before recommending one. Prices are estimates for the supplied dates and guests, with no inventory hold. Stays that fail the live check for those dates are left out, so a page can hold fewer than its limit. Nightly-rate filters use indexed average rates in SEK, not final stay totals. Pagination counts reflect the search index; current public rows may be fewer. Complete booking on the returned Guestit website link, which opens with the dates and guests filled in.

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": {
      "location_id": "<location_id>",
      "num_guests": "<num_guests>"
    },
    "name": "search_stays"
  }
}

Input Schema

NameRequiredDescriptionDefault
pageNo
sortNorelevance
limitNo
localeNoen
end_dateNoYYYY-MM-DD. Supply both dates. Check-in must be within 730 days and the stay cannot exceed 730 nights.
with_petsNo
num_guestsYes
start_dateNoYYYY-MM-DD. Supply both dates. Check-in must be within 730 days and the stay cannot exceed 730 nights.
location_idYes
min_bedroomsNo
nightly_rate_maxNoMaximum indexed average nightly rate in SEK. The final stay total includes the applicable fees.
nightly_rate_minNoMinimum indexed average nightly rate in SEK. This is not an all-in stay total.

Output Schema

NameRequiredDescriptionDefault
viewYes
staysYes
localeYesen
paginationYes
destinationsYes
calculated_atYes
requested_stayYes
applied_filtersYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.8/5.0
Behavior5/5

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

Annotations already declare readOnly and idempotent, but the description adds behavior the agent could not otherwise know: prices are estimates with no inventory hold, stays failing the live availability check are dropped so pages can be short, pagination counts come from the index rather than public rows, and booking completes on an external Guestit link.

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 purpose, then usage, then behavioral caveats, and nearly every sentence carries operational information. It is longer than typical and a few caveats (index vs. public counts, live check) could be merged, but nothing is filler.

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 12-parameter, 2-required search tool with an output schema, the description covers the preconditions, the pricing semantics, the availability filtering, the pagination quirk, and where the booking actually finishes. An agent could call this correctly and interpret short pages without further guessing.

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 only 33%, so the description carries real weight and does explain the two most confusing parameters: nightly_rate_min/max are indexed average rates in SEK, not all-in stay totals. It also pins location_id's provenance. It leaves page, limit, sort, locale, with_pets, and min_bedrooms unaddressed, though most are self-evident or enum-documented in the schema.

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?

Opens with a specific verb and resource ("Search Guestit apartments and holiday homes in Sweden") plus the key input requirement (location_id from resolve_destination). It is immediately distinguishable from compare_stays and stay_details, which are named as follow-up tools rather than search alternatives.

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?

Explicitly says to gather traveler dates and guest count before quoting, to refine by resending the full filter set, and to consult stay_details or compare_stays before recommending. Prerequisite (resolve_destination) and downstream handoffs are both stated, leaving little to inference.

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