Replace conflicting old term renderings in saved translations with the adjudicated final translation. Revalidates structure and logs every change for audit.
统一替换：把已落盘译文里撞车过的旧写法换成那一条的定译（裁决之后收口用；替换源只来自撞车证据，逐条重过结构校验并留痕）
| Name | Required | Description | Default |
|---|---|---|---|
| by | No | 谁批准这次替换（human / user / agent；模型身份会被拒） | |
| source | No | 只处理这一条术语的原文（不给 = 处理全部撞过车的） | |
| dry_run | No | 只算不写：先看会改几条、有没有过不了校验的 | |
| 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 |
Changes observed during successful MCP inspections.
v0.2.1Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare destructiveHint=true and readOnlyHint=false, so the write/destroy profile is covered structurally. The description adds genuinely non-obvious behavior: each replacement re-passes structural validation and leaves an audit trace (留痕), and the by-param note that model identity is rejected signals an approval/auth requirement. No contradictions.
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, front-loaded sentence with the verb 统一替换 leading, followed by scope and constraints in parentheses. No filler, but the heavy jargon and nested parenthetical reduce readability slightly.
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 destructive mutation tool with no output schema it covers what changes, that validation is re-run, that a trace is kept, and that approval is required. Return values are left to the dry_run preview semantics, which is acceptable given no output schema exists.
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 all five params are already well documented in the schema (by, source, dry_run, project, workdir). The description reinforces the semantics of source (only collision-derived entries) and the adjudication context, but adds little syntax or format detail 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?
The description names a specific operation (统一替换 – bulk replacement of previously-collided old wordings in already-written translations with the adjudicated fixed term). The verb+resource are concrete, though the domain jargon (撞车/定译) is dense. It does not differentiate itself from any sibling (e.g. revalidate, writeback), so it stays below 5.
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 gives a timing cue ('收口用' – to close things out after adjudication) and a scoping constraint (replacement source only from collision evidence). However, it names no alternative tools and gives no explicit when-not to use it, so usage is only implied.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.