Launches Genshin Impact with BetterGI and starts the screenshot tool, automatically entering the game; if startup exceeds the wait limit, check progress with bgi_status.
启动原神与 BetterGI 截图器（等价于 BetterGI.exe start），会联动启动游戏并自动进游戏。注意：游戏真正进到可操作状态要 1-2 分钟，超出单次调用上限（本机 MCP 约 60 秒）时会返回「仍在启动中」——这不算失败，随后用 bgi_status 复查即可。
| Name | Required | Description | Default |
|---|---|---|---|
| dry_run | No | 只打印命令不启动进程（默认 false） | |
| wait_seconds | No | 最多等多久找就绪证据（默认 40，上限 50） |
Changes observed during successful MCP inspections.
v1.0.0Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries the burden well: it discloses the 1-2 minute real startup time, the ~60s local MCP call ceiling, and that a 'still starting' return is not a failure. It omits idempotency behavior (effect if the game is already running) and process-side effects like spawning child processes.
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, front-loaded with purpose followed by the CLI equivalent and then the operational caveat. Every sentence carries information an agent needs to avoid misclassifying the timeout result.
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 annotations and no output schema, yet the description covers the timing profile, the timeout return shape, and the recovery path. What remains missing is the already-running case and the dry_run preview option, both of which an agent would want before calling.
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 dry_run and wait_seconds are already documented in the schema. The description's timeout discussion contextually relates to wait_seconds but never names or explains either parameter, so it adds no meaning beyond the schema. Baseline 3 applies.
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 action (launch Genshin + BetterGI screenshotter), anchored to a concrete CLI equivalent (BetterGI.exe start) and clarifies it chains into auto-login. An agent can distinguish this from bgi_close or bgi_status at a glance.
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?
Clearly implies use when the game is not running and explicitly routes the agent to bgi_status after a timeout return. It does not state exclusions (e.g. what to do if the game is already running) or prerequisites, so it falls short of a full when/when-not treatment.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.