Navigates to a specified WeChat mini-program page, waits, and collects CDP logs to verify page lifecycle events and errors.
跳转到指定页面，等待指定时间，通过 CDP 采集高清日志。 适用于页面生命周期日志检查（onLoad/onShow）、页面错误验证。 需先调用 wechat_automator(action='start') 并以 cdp_enabled=true 打开项目。 返回 JSON: {success, data: {current_page, cdp_logs}, message}。
| Name | Required | Description | Default |
|---|---|---|---|
| params | Yes |
| Name | Required | Description | Default |
|---|---|---|---|
| result | Yes |
Changes observed during successful MCP inspections.
v0.9.20Input schema / $defs / WechatNavigateInput / properties / cdp_port / descriptionPrevious value: -"CDP 调试端口。"New value: +"CDP 调试端口，不传则沿用本会话 wechat_ide(open) 的端口。"Input schema / $defs / WechatNavigateInput / properties / project_path / descriptionPrevious value: -"小程序项目路径（仅用于提示）。"New value: +"小程序项目路径，用于读 app.json 判断 tabBar 页；默认 WECHAT_PROJECT_PATH。"v0.9.16Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Beyond the annotations, it discloses the required session setup, that logs are captured via CDP after a wait, and that navigation triggers page lifecycle hooks. The safety profile (non-destructive, idempotent) is already covered by annotations, so the description fills in operational context rather than repeating it.
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?
Front-loaded with the action, then scenarios, then prerequisites, then return shape — a logical order with no filler. The return-value line is slightly redundant given an output schema exists but is short.
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?
A moderate-complexity mutation-ish tool with 9 parameters and an output schema; the description covers purpose, scenarios, prerequisites, and output shape, which is enough to call it correctly. It omits side effects on page state (navigation resets the current page) but nothing critical blocks invocation.
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 schema itself carries detailed per-field descriptions (timeout, wait_ms, cdp_port, detail_level, etc.), so parameter meaning is largely covered upstream. The description only alludes to waiting ('等待指定时间') and log collection, adding little syntax or coupling guidance 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 gives a specific verb-and-resource pair — navigate to a page and collect CDP logs — and adds the waiting behavior. It does not explicitly distinguish itself from siblings like wechat_inspector or wechat_screenshot, which agents could confuse with log/debug inspection.
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 names concrete scenarios (checking onLoad/onShow lifecycle logs, verifying page errors) and a hard prerequisite (wechat_automator(action='start') with cdp_enabled=true). It stops short of stating when not to use it or which sibling to pick for pure inspection.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.