Ask the directory a customer question in natural language. Returns schema.org cards of businesses that genuinely answer it (LLM-reranked, strictly from the directory — never invented) + grounding links. Use when the customer describes a NEED rather than a search term.
| Name | Required | Description | Default |
|---|---|---|---|
| language | No | Optional service language filter (ISO code) | |
| question | Yes | Customer question |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Describes key behaviors: LLM-reranking, strictly from directory (never invented), and grounding links. No annotations exist, so description carries the burden; it's mostly transparent but lacks side effects or permission details.
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 concise sentences covering purpose, output, and usage guidance. No wasted words.
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?
Given two parameters and no output schema, the description fully explains input, output format (schema.org cards + grounding links), and behavior (LLM-reranked, no invention). No missing critical info.
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 coverage is 100% with parameter descriptions. The description adds little beyond clarifying that 'question' is a natural language query. Baseline 3 appropriate since schema is already sufficient.
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?
Clearly states the tool answers customer questions in natural language, returning schema.org cards of relevant businesses. Differentiates from sibling tools (search_businesses likely keyword-based, get_business specific) by focusing on natural language needs.
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?
Explicitly advises when to use: when the customer describes a NEED rather than a search term. This provides clear guidance vs. sibling tools.
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 clear, distinct purpose: ask_directory for natural language queries about customer needs, search_businesses for keyword-based search, and get_business for retrieving full details by slug. No overlap.
All tools use a consistent verb_noun pattern in snake_case (ask_directory, get_business, search_businesses), making them predictable and easy to understand.
With 3 tools, the server is lean but covers the core operations for a business directory: search, ask, and retrieve details. While minimal, it is appropriate for the domain and avoids unnecessary complexity.
The tool set covers search, natural language query, and detail retrieval. Minor gaps exist (e.g., no explicit filtering by category), but the tools are well-designed to handle common workflows and can work around limitations via the query parameter.
