Modify a game localization configuration value (API key, base URL, model), targeting the project layer by default or --global to apply across all projects.
修改一项配置；默认改项目层，--global 改全局层（一次配好、所有项目通用）
| Name | Required | Description | Default |
|---|---|---|---|
| key | No | 配置项（含 api_key / base_url / model） | |
| value | No | 新值 | |
| project | No | 游戏项目根目录（默认当前目录） | |
| workdir | No | 工作区目录，默认 <项目>/.gametrans | |
| global_scope | No | 写全局层（~/.gametrans），而不是当前项目 |
Changes observed during successful MCP inspections.
v0.2.1Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint=false and destructiveHint=true, so the mutation/overwrite risk is signalled structurally. The description adds the scope-selection behavior but never confirms what happens to an existing value, whether a write is destructive to the prior setting, or what the return looks like — modest added value over annotations.
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?
A single compact sentence plus a parenthetical; the default behavior and the global-layer override are front-loaded with no filler. Efficient and well-ordered.
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?
Tool has annotations, full schema coverage, and no output schema, so the burden is light and the scope ambiguity is addressed. However, as a destructive write tool it should say whether setting a key overwrites an existing value, which is the main remaining gap.
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 key/value/project/workdir/global_scope are already documented. The description reinforces the layer semantics (project default vs global) but adds no syntax or format detail beyond the schema, so baseline 3 applies. Note it references a '--global' flag while the schema exposes a boolean 'global_scope' param, which could mildly confuse mapping.
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 (修改) and resource (一项配置), and immediately clarifies the two scope layers (项目层 vs 全局层). It is distinguishable from config_show/config_unset/config_path by the write verb, though it never names those siblings explicitly.
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?
Explains the default (project layer) and the opt-in alternative (global layer, 'once configured, applies to all projects'), which is genuine when-to-use guidance. It does not clarify when to use this over config_unset or any prerequisite state, so guidance stays implied rather than explicit.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.