tours_listEscorted group tours from Tirana with Albanian-speaking guides (cached catalogue): stable id, title, days/nights, cities, transport, next_departure and the PER PERSON price in EUR — unlike charter packages, tour prices are per person. For one tour's full calendar, program and date-specific price use tour_details.
| Name | Required | Description | Default |
|---|---|---|---|
| limit | No | Max tours to return (default 10). |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already indicate read-only, idempotent, non-destructive behavior. The description adds valuable context beyond annotations by disclosing that the catalogue is cached, that IDs are stable, and that prices are per person rather than per package. This helps the agent set expectations about data freshness and price interpretation.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is dense but every clause carries useful information: scope, guide language, cache status, field list, pricing rule, and sibling routing. The most important identifying details are front-loaded, and the alternative tool is mentioned at the end without bloat.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a simple, read-only list tool with one optional parameter and no output schema, the description is complete. It enumerates the returned fields, clarifies sorting via the title, notes the cache behavior, and directs the agent to tour_details for deeper information. Nothing essential is missing.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The schema covers the single optional limit parameter fully with a description including default and constraints. The tool description does not need to repeat this, so the baseline of 3 is appropriate. No additional parameter meaning is required.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool lists escorted group tours from Tirana with Albanian-speaking guides and specifies the exact fields returned. It further distinguishes itself from charter packages by noting per-person pricing, and points to tour_details for a single tour's full details. This leaves no ambiguity about what the tool does or how it differs from siblings.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description explicitly tells the agent to use tour_details when a single tour's full calendar, program, or date-specific price is needed. It also contrasts tours_list with charter packages, clarifying that price semantics differ. This is strong routing guidance that helps the agent choose the correct tool.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Add one secure layer between your agents and this server.
Most tools have clearly distinct roles, and the charter_* family is carefully delineated (cheapest by destination, cheapest by date window, filtered discovery, single hotel, comparison). There is still some surface-level overlap between charter_cheapest, charter_flexible_dates, and charter_offers, though the descriptions do enough to prevent major misselection.
The naming is generally consistent and readable: charter_* tools share a strong prefix, and hotel_details/compare_hotels/tours_list/tour_details follow predictable noun-based patterns. Minor deviations like booking_link (verb+noun) and prices_digest (noun+noun) do not create real confusion.
Twelve tools is well within the ideal range for a travel-domain server, and each tool covers a distinct query pattern: discovery, cheapest pricing, flexible dates, specific hotels, comparisons, static details, tours, and booking links. The count feels justified rather than padded.
The surface covers the main user journey well: find charters, filter by budget/features, compare hotels, get hotel details, check tours, and obtain booking links. Minor gaps exist, such as no non-charter package filtering by date/budget and no standalone flight/transfer search, but agents can still complete realistic travel-planning tasks.