Agent-native insurance quoting protocol — sandbox, MCP + REST, eligibility pre-flight
Scored across 3 tools
checkEligibility is explicitly a pre-flight eligibility check, while getAutoQuotes and getHomeQuotes are full pipeline operations for two clearly distinct insurance products. There is no meaningful overlap between the tools, so an agent should be able to select the right one without confusion.
All three tool names follow the same camelCase verb-first convention: checkEligibility, getAutoQuotes, getHomeQuotes. The verbs differ (check vs. get) but that matches their distinct actions, and the naming pattern is predictable.
Three tools is a well-scoped set for a focused quoting service: one shared eligibility gate and one dedicated quoting pipeline per product line. Each tool earns its place, and the count falls comfortably within the ideal 3-15 range.
The tool surface covers the core quoting lifecycle: an upfront eligibility check followed by full quote generation for both supported lines, auto and home. There are no obvious dead ends or missing operations for the apparent purpose of this server.
Quick pre-flight eligibility check with partial data.
Use this FIRST in any intake flow — surfaces hard stops after 2-3 fields without collecting all 40+. Blocks known-decline scenarios before any adapter dispatch.
| Name | Required | Description | Default |
|---|---|---|---|
| fields_json | Yes | JSON object with partial fields. auto examples: {"salvage_title": true}, {"rideshare_use": true} home examples: {"plumbing_material": "polybutylene"}, {"panel_type": "federal_pacific", "wiring_type": "knob_and_tube"} | |
| policy_type | Yes | "auto" or "homeowners" |
| Name | Required | Description |
|---|---|---|
| result | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already mark this as read-only, idempotent, and non-destructive. The description adds useful behavioral context beyond that: it operates with only 2-3 fields, surfaces hard stops, and blocks known-decline scenarios before dispatching adapters. There is no contradiction with the 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 short sentences with the core purpose front-loaded. Every sentence earns its place: what it is, when to use it, and what behavior it provides. No filler or redundant restatement of the tool name.
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?
With an output schema present, annotations covering the safety profile, and detailed parameter documentation, the description is mostly complete for correct invocation. The only minor gap is not explicitly linking this check to the next step with the sibling quote tools, though 'FIRST' and 'before adapter dispatch' strongly imply the flow.
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 the schema already fully documents both parameters with concrete examples for policy_type and fields_json. The description's references to 'partial data' and '2-3 fields' add mild context but no new parameter-level semantic information beyond the schema.
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 states a specific verb and resource: a 'pre-flight eligibility check' that 'surfaces hard stops' from partial data. This clearly distinguishes it from the sibling quote-retrieval tools, which focus on getting auto or home quotes rather than checking eligibility first.
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?
It gives explicit placement: 'Use this FIRST in any intake flow' and explains it works before full data collection and before adapter dispatch. It stops short of naming the sibling tools as the follow-up step or stating when not to use it, so it is clear but not exhaustive.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Run the full auto insurance quoting pipeline.
| Name | Required | Description | Default |
|---|---|---|---|
| auto_input_json | Yes | JSON string of the full AutoInput model. Required keys: garaging_address, drivers[], vehicles[], coverage See engine/validator.py AutoInput for full schema. |
| Name | Required | Description |
|---|---|---|
| result | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint=true, idempotentHint=true, and destructiveHint=false, covering the safety profile. The description adds no behavioral context beyond repeating that it runs a pipeline, so it does not disclose other relevant behaviors such as whether it returns stored quotes, performs external lookups, or has side effects.
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 description is very short and front-loaded, which is good, but it is also under-specified. A single sentence conveys the general purpose but does not enrich the tool definition enough to justify a higher score.
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 one parameter, complete schema documentation, output schema presence, and safety annotations, so the minimal description may suffice for a simple invocation. However, it lacks guidance on distinguishing this from sibling tools and does not clarify what 'full pipeline' means in practice, leaving some ambiguity.
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%, so the auto_input_json parameter is fully documented in the schema, including required keys and a reference to the full AutoInput model. The description adds little beyond the schema, so 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?
The description uses a specific verb ('Run') and identifies the resource ('the full auto insurance quoting pipeline'). It distinguishes itself from siblings by focusing on a comprehensive auto quote, versus checkEligibility for eligibility and getHomeQuotes for home quotes, though it does not explicitly state those distinctions.
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 phrase 'full auto insurance quoting pipeline' implies this tool is for generating complete auto insurance quotes, but the description provides no explicit guidance on when to prefer it over checkEligibility or getHomeQuotes. Usage context is implied rather than stated.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Run the full homeowners insurance quoting pipeline.
| Name | Required | Description | Default |
|---|---|---|---|
| home_input_json | Yes | JSON string of the full HomeInput model. Required keys: property_address, named_insured, property, hazards, coverage See engine/validator.py HomeInput for full schema. |
| Name | Required | Description |
|---|---|---|
| result | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already cover the safety profile with readOnlyHint, idempotentHint, and destructiveHint, so the description does not need to restate those. The description adds only that this is a composite 'full' pipeline, but it does not disclose any additional behavioral characteristics such as external calls, required dependencies, or failure modes. There is no contradiction with 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?
The description is a single efficient sentence with no filler or redundancy. It front-loads the action and resource, though it is minimal and could include more scoping guidance without becoming verbose.
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 output schema and parameter schema cover return values and input format, so those are not gaps. However, the description does not explain how this tool fits into the broader quoting flow relative to checkEligibility or getAutoQuotes, leaving the agent to infer ordering and prerequisites.
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?
The only parameter, home_input_json, is fully described in the input schema with required keys and a pointer to the full HomeInput model. The tool description adds no parameter-level detail, but because schema description coverage is 100%, the baseline of 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?
The description clearly identifies the action (run) and the resource (full homeowners insurance quoting pipeline). It is distinguishable from the siblings getAutoQuotes and checkEligibility via the terms 'homeowners' and 'quoting', but 'full pipeline' remains somewhat abstract and does not enumerate what stages are included.
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 provides no explicit guidance on when to use this tool versus checkEligibility or getAutoQuotes. There is no mention of ordering, preconditions, or cases where one of the sibling tools would be more appropriate. Usage context must be inferred entirely from the tool name and sibling list.
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.
checkEligibilitygetAutoQuotesgetHomeQuotesReal, bindable home & auto insurance quotes via MCP (Texas, expanding); human-completed bind.
Agent-native commerce: real quotes, reversible holds, and a whole business you own.
Insurance brokerage for AI agents — quote, bind, and settle in USDC
Agent-to-business commerce sandbox: intents, offers, bookings. Demo data, ed25519-signed calls.
Add one secure layer between your agents and this server.