bazi.compare_chartsCompare two BaZi charts to get side-by-side structural evidence like day master, cross-chart stems and branches, and shensha, without marriage scores or annual luck overlays.
对当前用户的两张八字记录（或一侧本人资料）执行原局直接结构对照，返回基础排盘留痕、日元/日支、跨盘干支与神煞并列证据；不输出统一合婚分数，不判断合化成立，不叠加双方岁运。
| Name | Required | Description | Default |
|---|---|---|---|
| left_record_id | No | ||
| right_record_id | No | ||
| left_use_profile | No | ||
| right_use_profile | No |
Changes observed during successful MCP inspections.
v1.0.1Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Beyond readOnlyHint=true, the description discloses the output boundary clearly: it returns raw structural evidence and calculation traces rather than a verdict, and explicitly declines to judge 合化 or fold in 岁运. That is exactly the kind of scope-limiting context annotations cannot convey, though it says nothing about result size or ordering.
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?
One dense sentence with the scope and action front-loaded, followed by the output inventory and the negative constraints. Every clause carries information; the only cost is that the multiple semicolon-separated exclusions are packed tightly enough to read as a run-on.
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?
For a 4-parameter read-only tool with no output schema, the description covers action, scope, output contents, and explicit non-outputs, and it states that both records belong to the current user. The remaining gap is operational rather than semantic: nothing explains the record-or-profile exclusivity encoded in the schema.
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 has no parameter documentation, so the oneOf structure (each side must supply either a record_id or a use_profile flag) is left ambiguous. The phrase '（或一侧本人资料）' hints at the profile variant but does not explain that exactly one of the two options is required per side.
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: direct structural comparison of the 原局 (natal charts) of two bazi records, and enumerates what the output contains (day master/day branch, cross-chart stems and branches, shensha side-by-side evidence). It distinguishes itself from a group comparison only implicitly via '两张' (two charts) rather than naming bazi.compare_group_charts.
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 three explicit exclusions (no unified compatibility score, no 合化 determination, no overlaying of 岁运) tell the agent when this tool is the wrong pick even without naming an alternative, and '（或一侧本人资料）' clarifies the profile-vs-record choice. What's missing is a direct pointer to the sibling tool to use instead when a scored 合婚 result is wanted.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.