Creates an experimental branch for parallel A/B testing by copying inputs from the current HEAD or another branch; optionally writes the experiment purpose to NOTES.md.
创建实验分支，默认复制同源 inputs
| Name | Required | Description | Default |
|---|---|---|---|
| from | No | 从哪个分支复制，默认当前 HEAD | |
| name | Yes | 实验分支名（只能用小写字母、数字、连字符；main 是保留名） | |
| root | Yes | Conversation Branch 工作区根目录 | |
| purpose | No | 实验目的/假设，写入 NOTES.md | |
| no_copy_inputs | No | 不复制 inputs（默认会复制） |
Changes observed during successful MCP inspections.
v0.1.0Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
The annotations already mark this as a mutating but non-destructive operation. The description adds the key behavioral detail that inputs are copied by default, which is not visible from annotations alone. Secondary effects such as NOTES.md updates are left to the schema, but the core side-effect is disclosed.
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?
The description is a single front-loaded sentence with no redundant content. The default-copy clause earns its place as the key non-obvious behavior.
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?
The description plus schema is sufficient to invoke the tool, but it leaves some workflow context unspecified: when to choose cb_branch over related tools, what '同源 inputs' exactly refers to, and what a successful creation returns. For a five-parameter mutation tool with sparse annotations and no output schema, a bit more context would be expected.
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 schema already documents all five parameters, including defaults for from and no_copy_inputs. The description's '默认复制同源 inputs' reiterates the default-copy behavior in more human terms but does little beyond what the schema already provides.
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 uses a specific verb (创建/creates) with a concrete resource (实验分支/experimental branch) and adds a default behavior (copying inputs). This makes it easy to distinguish from sibling tools like cb_checkout, cb_rename, or cb_discard, which operate on branches rather than create them.
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?
The intended use is implied by the verb and resource—create an experimental branch—but the description gives no explicit when-to-use guidance or exclusions. It does not mention alternatives such as cb_checkout for switching or cb_promote for integrating, so the agent must infer the usage context from the sibling names.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.