获取调用策略和字段优先级。调用流程：(1)收集用户age后即可调recommend(2)有health_conditions时自动附带核保结论(3)include_reasoning默认false,Agent自行组织语言(4)返回的source_url可直接给用户作为投保链接。本工具返回各能力的字段优先级、缺失影响、默认行为。
| Name | Required | Description | Default |
|---|---|---|---|
| capability | No | 想了解哪个能力，不传则返回全部 |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Without annotations, the description carries full burden. It discloses output components and that source_url can be directly given to users, but does not mention if the tool is read-only, authorization needs, or other behavioral traits.
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 longer than necessary and includes a call flow that seems more relevant to sibling tools. It could be more focused on what get_schema does.
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 no output schema, the description adequately explains the return values: field priorities, impacts, default behavior, and source_url. It is sufficient for an agent to understand what to expect.
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 parameter is fully documented in the schema. The description adds little beyond restating that it returns field priorities for each capability.
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 that the tool returns field priorities, missing impacts, and default behaviors for each capability. It distinguishes itself from sibling tools like recommend or search by focusing on metadata about those capabilities.
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 includes a call flow that implies order of usage for other tools but does not explicitly state when to use get_schema itself. It lacks guidance on alternatives or when not to use it.
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: answer_question handles factual queries, chat manages multi-turn dialogue, check_underwriting assesses health risks, compare_products compares specific products, get_premium provides precise pricing, get_product_detail retrieves product info, get_schema guides strategy, recommend gives tailored plans, and search_products filters by criteria. No two tools overlap in functionality.
All tool names follow a consistent verb_noun pattern in snake_case (e.g., answer_question, check_underwriting, compare_products, get_premium, get_product_detail). The few single-word tools (chat, recommend) are common exceptions that still convey action clearly.
With 9 tools, the server is well-scoped for an insurance advisor. Each tool serves a necessary function—knowledge retrieval, chat, underwriting, comparison, pricing, details, meta-guidance, recommendation, and search—without redundancy or bloat.
The tool set covers the full lifecycle of insurance advisory: product discovery (search, detail, compare), pricing (get_premium), risk assessment (check_underwriting), recommendation (recommend), knowledge support (answer_question), and user guidance (chat, get_schema). No obvious gaps remain for typical use cases.
