Safely edit BetterGI's config.json with automatic backup and verification, requiring BetterGI closed; dry_run previews changes without writing.
安全修改 User\config.json（父.子=值）。要求 BetterGI 已退出；会自动备份并回读校验。dry_run=true 只预览。
| Name | Required | Description | Default |
|---|---|---|---|
| changes | Yes | 形如 [{path:"autoDomainConfig.condensedResinUseCount", value:"5"}] | |
| dry_run | No | 只预览不写入（默认 false） |
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 full behavioral burden and does well: it discloses the pre-call precondition, that an automatic backup occurs, and that a read-back verification follows the write. It does not say what happens on an invalid path, whether missing keys are created, or how errors surface, leaving a real gap.
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, front-loaded with the action and target, followed by preconditions and side effects. Nothing is redundant with the name or schema, and every clause carries actionable information.
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 two-parameter mutation tool with no annotations and no output schema, it covers safety, preconditions, and side effects well. It leaves the caller without any notion of the response or error/failure behavior, which matters for a config-writing tool the user cannot run while the app is active.
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 baseline is 3, and the description adds beyond it by expressing the path format as 父.子 (dot-separated parent.child) and reinforcing dry_run as a preview-only flag. It does not explain batching semantics or ordering of multiple entries in the changes array.
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 names a concrete verb (安全修改/safely modify) and a concrete resource (User\config.json), plus the addressing syntax (父.子=值). That is far more specific than the name alone. It stops short of explicitly contrasting with siblings like bgi_js_settings or bgi_set_onedragon, which also write configuration, so differentiation is inferential.
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 states a hard prerequisite (BetterGI must be exited) and clarifies the preview mode (dry_run=true), which is exactly the context an agent needs before calling. No alternative tool or when-not-to-use case is named, so it falls short of the top mark.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.