The IRIS distress screen: carriers whose NAIC annual-statement filing reports a published, NON-ZERO count of IRIS ratios outside the usual range for a fiscal year (NULL/unpublished years are excluded, never read as zero). Filter by year; a carrier can appear more than once across years. $0.10 per query. Free discovery: /v1/financials/sample.
| Name | Required | Description | Default |
|---|---|---|---|
| year | No | ||
| limit | No |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries full burden and does well by disclosing that NULL years are excluded (never read as zero), carriers may appear multiple times across years, and cost per query. It does not contradict any annotations.
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?
Three sentences: core purpose, important behavioral details, and pricing. It is front-loaded and each sentence adds value, though it could be more structured.
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 exists and the description does not specify the return format or fields. While it mentions IRIS ratios, it leaves the agent guessing about what data will be returned, making it incomplete.
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 0% and the description only mentions filtering by year, leaving the 'limit' parameter unexplained. This under-documents the parameters, failing to compensate for the schema gap.
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 identifies the tool as an IRIS distress screen that returns carriers with a published, non-zero count of IRIS ratios outside the usual range. This is specific and distinguishes it from sibling financial tools like get_carrier_financials or get_financials_reinsurers.
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 mentions filtering by year and provides pricing info, but does not give explicit guidance on when to use this tool versus other financial tools. It implies a specialized use case but lacks comparative context.
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, covering different data types (carriers, financials, catastrophes, hazard, etc.) and actions. Even closely related tools like compare_states and compare_carrier_states differ in scope (state comparison vs. carrier footprint), so no ambiguity exists.
The vast majority follow a verb_noun pattern with 'get_' for retrieval and 'list_' for enumeration. A few tools use 'compare_' and 'check_', which are semantically appropriate but introduce slight inconsistency. Overall, the pattern is predictable and readable.
With 40 tools, the count is well above the typical 3-15 range, making it feel heavy. While the domain justifies many endpoints, the presence of over 10 dedicated sample tools adds unnecessary bloat. Consolidation of sample tools could improve scoping.
The server covers a wide range of insurance data domains: eligibility, carriers, financials, catastrophe, hazard, litigation, premium, rates, syndicates, and enforcement. It includes discovery tools and sample data. As a read-only API, it is comprehensive, though a tool for policy-level detail might be a minor gap.
