Takes a natural language business description and returns matched class codes (NAICS, ISO GL, NCCI WC). Always call this first to understand the user's business type before making recommendations.
| Name | Required | Description | Default |
|---|---|---|---|
| state | No | Two-letter state code | |
| business_description | Yes | User's description of their business |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries the full burden. It states the action (takes and returns) but does not disclose whether the operation has side effects, requires authentication, or is read-only. Given the lookup nature, this is adequate but not thorough.
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 deliver the function and usage guidance with no filler. The information is front-loaded and each sentence earns its place.
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 the absence of an output schema and annotations, the description provides essential details: what it does, what it returns, and when to use it. It could detail return structure or state handling, but the current description is sufficient for a classification tool.
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 description coverage is 100%, so both parameters are already documented. The tool description reinforces the primary role of business_description but does not add new meaning beyond the schema, especially for the state parameter.
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's function: taking a natural language business description and returning matched class codes (NAICS, ISO GL, NCCI WC). This distinguishes it from sibling recommendation tools by positioning it as the upfront classification step.
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 says 'Always call this first' and explains why (to understand the user's business type before making recommendations). This provides clear when-to-use guidance and implies ordering against the other 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 distinct purpose: classification, coverage suggestions, explanations, carrier recommendations, and agent handoff. There is no overlap between tools; even the recommendation-focused tools operate on different layers (coverage vs. carrier).
All tool names follow a consistent verb_noun snake_case pattern (classify_business, connect_with_agent, explain_coverage, get_carrier_recommendations, suggest_coverages). The naming is predictable and clearly indicates the action and target.
With 5 tools, the server is well-scoped for its purpose of guiding small businesses through insurance discovery and connection. Each tool serves a necessary step in the workflow, and none feel redundant or excessive.
The tool set covers the full journey from business classification to coverage suggestions, educational explanations, carrier recommendations, and human agent handoff. No obvious missing capabilities for the stated purpose of the server.