Skip to main content
Glama
Sign In

Adónde

by com.getadonde
OverviewDiscussionsAdmin

Search tours

search_tours
Read-onlyIdempotent

Searches bookable tours and experiences in a city, best first. Returns the top 8 by default (limit up to 50, offset to page), each with product_code, rating, price, duration, book_link and details_link on getadonde.com, plus next with the steps left. With date, tours not running that day are left out and start times shown; without one, runs_on_date is null, so never say a tour runs on a day you did not search. Reads only; nothing is booked. Use get_tour_details for one tour in depth, compare_tours for 2 to 4 side by side, get_menu for tours already on a trip's menu.

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": {
      "city": "<city>"
    },
    "name": "search_tours"
  }
}

Input Schema

NameRequiredDescriptionDefault
cityYesCity or town, e.g. Lisbon.
dateNoA day to check, YYYY-MM-DD: keeps only tours that run then, with start times.
limitNoHow many tours to return, up to 50 (default 8).
queryNoA word in the title, e.g. food or boat.
offsetNoSkip this many ranked tours (default 0). For 'more', pass the previous offset plus limit.
countryNoCountry name, e.g. Portugal. Send it when known; it keeps same-named cities apart.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.6/5.0
Behavior4/5

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

Adds substantial behavior beyond the annotations (which already declare readOnly/destructive=false/idempotent): default page size of 8, max 50, offset paging, a 'next' field with steps left, and the critical caveat that runs_on_date is null when no date is passed so the agent must not assert a tour runs that day. The only gap is that 'Reads only; nothing is booked' partly restates readOnlyHint.

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-loads the verb, scope and ranking, then layers return shape, date semantics, safety and alternatives in that order with no filler. It is a single dense paragraph though; splitting return-shape from routing guidance would scan faster, keeping it just below top marks.

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?

No output schema exists, yet the description enumerates the returned fields (product_code, rating, price, duration, book_link, details_link, next) and the date-dependent null, so an agent knows what it will get. For a 6-parameter, schema-covered read tool this covers everything needed to call it correctly.

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 the baseline is 3, but the description adds cross-parameter meaning the schema cannot: the date parameter changes result composition (non-running tours dropped, start times shown) and limit/offset tie to the returned 'next' field. Country's disambiguation rule is also echoed, though query/city are left to 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?

Names a specific verb and resource ('Searches bookable tours and experiences in a city'), states the ranking and the city scope, which immediately distinguishes it from get_tour_details and get_menu. An agent knows exactly what this tool returns 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 Guidelines5/5

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

Explicitly routes three alternatives: get_tour_details for one tour in depth, compare_tours for 2-4 side by side, get_menu for tours already on a trip's menu. The conditional 'Use X for Y' form leaves nothing for the agent to infer about tool selection.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

All Adónde toolsInspect
Try in Browser
One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources