AI-native parametric insurance infrastructure. Assess weather risk, generate quotes, bind policies, and monitor triggers programmatically. Live paid endpoint via x402 (USDC on Solana).
Scored across 1 tool
With only one tool, there is no risk of selecting the wrong tool or confusing overlapping purposes. The tool's function, retrieving historical weather statistics for a location and business type, is clear enough in the set context.
The single tool name get_weather_history follows a clear snake_case verb_noun convention. With only one tool there are no deviations or mixed naming styles to create inconsistency.
A single-tool server is thin for most practical tool surfaces, even when the one operation is focused. It leaves little room for discovery, related queries, or lifecycle operations that agents may reasonably expect.
The surface covers one historical-weather lookup but lacks supporting operations such as location or business-type discovery, current conditions, forecasts, or metadata endpoints. Licensing and rate-limit requirements are embedded in prose rather than represented as usable tooling.
Returns historical weather statistics for a location and business type, with limitations. Official Anthropic connector IP ranges share 100 free calls per day; official OpenAI connector IP ranges share a separate 100. Other IP addresses receive 10 free calls per day. A combined 300-free-call daily cap covers all pools, including cached results. Resets at midnight UTC; additional calls require $0.10 Solana USDC via x402. Always show the licensing_disclosure to the user verbatim with any results from this tool. Do not comment on insurance pricing, premiums, or whether coverage is advisable.
| Name | Required | Description | Default |
|---|---|---|---|
| location | Yes | City and state of the business, e.g. 'Tampa, FL' or 'Kansas City, MO'. | |
| business_type | Yes | Caller-provided business category for context only, not business-specific loss modeling. |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint=true, but the description adds substantial behavioral context: tiered free-call quotas, a combined 300-call cap, UTC reset, paid calls via USDC, required licensing disclosure, and content restrictions. It does not describe the actual return format or historical coverage, but the rate/cost/legal behavior is unusually well disclosed.
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 purpose is front-loaded, but the description is then dominated by lengthy quota, payment, and legal-disclosure text. Those details are relevant, yet the structure emphasizes operational terms over what the statistics contain. It is informative but not tightly 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?
The tool has only two parameters and no output schema, so the description should clarify what historical statistics are returned, such as time range, metrics, or output shape. Instead it focuses almost entirely on quotas, payment, and legal constraints. Core return behavior remains underspecified.
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%, and the schema documents both parameters, including the business_type enum and its 'context only' caveat. The description mentions location and business type but adds no meaning beyond the schema. Baseline 3 is appropriate.
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?
States a specific verb and resource: returns historical weather statistics for a location and business type. The phrase 'with limitations' is vague, but the core purpose is clear. No sibling tools exist, so sibling differentiation is not applicable.
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?
Provides operational constraints such as free-call quotas, paid overage, licensing disclosure, and a restriction on insurance commentary. However, it does not explicitly say when to use this tool versus alternatives or when not to use it. With no sibling tools, the guidance is implied rather than complete.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
get_weather_history1 field changedInput schema / properties / business_type / enumPrevious value: -[
- "restaurant",
- "car_wash",
- "retail",
- "agriculture",
- "event_venue"
-]New value: +[
+ "restaurant",
+ "car_wash",
+ "retail",
+ "agriculture",
+ "event_venue",
+ "golf_course",
+ "construction",
+ "hotel",
+ "resort",
+ "marina",
+ "boat_rental",
+ "winery",
+ "vineyard",
+ "hoa_condo",
+ "landscaping",
+ "tour_operator",
+ "outdoor_retail",
+ "casino",
+ "real_estate",
+ "property_management",
+ "food_truck",
+ "delivery_service",
+ "logistics",
+ "solar_farm",
+ "other"
+]assess_weather_riskbind_policycheck_triggerget_parametric_quoteget_policy_statusget_weather_historylist_carriersassess_weather_riskbind_policycheck_triggerget_parametric_quoteget_policy_statuslist_carriers
Add one secure layer between your agents and this server.