Performs an autocomplete typeahead search for a query (e.g., 'bandung', 'hilton'). Returns a list of locations, hotels, restaurants, or attractions with their respective geoId.
| Name | Required | Description | Default |
|---|---|---|---|
| lang | No | Optional language code (e.g. 'en_US'). | |
| query | Yes | The search query string. | |
| currency | No | Optional currency code (e.g. 'USD'). |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description carries full responsibility for behavioral disclosure. It does not explicitly state that this is a read-only operation, does not mention rate limits, result limits, ordering, or error behavior. It only discloses that it returns a list with geoId, which is insufficient for full transparency.
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 two sentences, front-loaded with the primary action and output, and contains no filler. Every word contributes value, and the examples are useful and concise.
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 tool with three parameters and no output schema, the description adequately explains the purpose and return type. It covers the query parameter through examples and the return value via 'list ... with geoId.' However, it lacks details on result limits or ordering, which prevents a perfect score.
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 input schema has 100% parameter description coverage, so the baseline of 3 applies. The description adds a small amount of value by showing example queries ('bandung', 'hilton'), but it does not elaborate on parameter meaning beyond what the schema already provides.
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 performs an autocomplete typeahead search with specific verb and resource ('Performs an autocomplete typeahead search') and describes the output (list of locations/hotels/restaurants/attractions with geoId). It distinguishes itself from siblings like get_details and search_listings by focusing on typeahead/autocomplete behavior.
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 implies usage for autocomplete/typeahead scenarios through its wording and examples, but it does not explicitly state when to use it versus alternatives like search_listings, nor does it mention exclusions. No when-not-to-use guidance is provided, leaving it at implied usage level.
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.
While most tools have clear specific purposes, 'get_details' overlaps with 'get_poi_full_about' and could be confused with the more specific getters like 'get_poi_amenities' or 'get_poi_reviews'. The distinction between a generic details endpoint and a detailed metadata profile is not immediately obvious.
The naming convention is mixed: most tools use a 'get_' prefix (get_details, get_media_gallery, get_poi_*), but 'search_listings', 'typeahead', and 'usage_statistic' break that pattern. The verbs are also inconsistent (get vs search vs typeahead), making the set feel less predictable.
With 8 tools, the server is well-scoped for a travel and POI information service. Each tool serves a distinct purpose in the overall workflow of searching, retrieving details, and viewing ancillary data like media, amenities, and reviews. No tools feel redundant or excessive.
The toolset covers the core needs for exploring Points of Interest: search/typeahead, detailed information, media, amenities, reviews, and API usage stats. A minor gap is the lack of a direct 'get_poi_by_id' function, but 'get_details' likely covers that. The available tools form a coherent workflow without major dead ends.