Town knowledge layer: open-late, essentials, eat, with-kids, working-in, hospital-visitor, itineraries. Unbuilt topic returns 'not yet published' plus the town guide root.
| Name | Required | Description | Default |
|---|---|---|---|
| town | Yes | ||
| topic | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Description adds useful behavioral info: unbuilt topics return 'not yet published' plus the town guide root. This complements annotations (readOnlyHint, openWorldHint). No contradiction.
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?
Two sentences, front-loaded with purpose, no redundant words. Efficient.
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?
No output schema; description explains behavior for unbuilt topics but does not describe normal return structure or data format. Adequate but could be more complete.
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?
Schema has 2 params with 0% description coverage. Description lists some topic enum values but not all (missing 'things-to-do'). Adds marginal value; does not fully compensate for lack of parameter documentation.
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?
Description clearly specifies the tool returns town guide content for specific topics, listing examples. It distinguishes from sibling tools like check_availability or create_enquiry.
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?
No guidance on when to use this tool vs alternatives. Does not mention when not to use or provide recommended scenarios.
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.
Each tool has a clearly distinct purpose: availability returns a pre-filled link, enquiries are separated by type, corporate info is separate from general property info, distances vs events vs rates vs room types vs town guide vs search vs recommendation. The only potential confusion is between create_enquiry and create_corporate_enquiry, but descriptions clarify the target audience. Overall, no ambiguity.
All tool names consistently follow a verb_noun pattern in snake_case (e.g., check_availability, get_distances, create_enquiry). The verbs are appropriate (check, create, get, recommend, search) and nouns clearly indicate the resource. No mixing of styles or vague verbs.
With 12 tools, the server is well-scoped for a hotel information and enquiry system. Each tool covers a distinct aspect of the domain without overlap or unnecessary bloat. The count is within the optimal range (3-15) for an MCP server.
The tool set covers core hotel information retrieval (property, rooms, rates, distances, events, town guide) and enquiry creation (general and corporate). However, there is no tool to complete a booking or confirm availability beyond a link. This is a minor gap; agents must hand off to the booking engine. Overall, the surface is mostly complete for its stated purpose.
