Promote a candidate agent definition to current, overwriting the existing version. Requires explicit human confirmation to execute this destructive change.
晋升 candidate 为 current。🔴 破坏性，必须 human_confirmed:true。
| Name | Required | Description | Default |
|---|---|---|---|
| comment | No | 决策备注（写入 decision-log，如审批人/理由） | |
| current | Yes | 当前版本 Agent 定义路径（晋升目标——被覆写方） | |
| candidate | Yes | 候选版本 Agent 定义路径（晋升来源） | |
| human_confirmed | No | 🔴 人工确认：false/缺省=挂起等人审（默认）；true=执行晋升。破坏性操作不允许自动执行 |
Changes observed during successful MCP inspections.
v0.1.0Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries the full burden of behavioral disclosure. It does warn that the operation is destructive and requires human confirmation, which is valuable for a mutation tool. However, it does not explicitly state whether the current value is irreversibly overwritten or describe other side effects such as decision-log writes beyond what the schema already shows.
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 extremely compact and front-loaded, with the core action and the critical destructive warning stated first. Every sentence carries essential information, and there is no redundancy or filler.
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 definition gives the core purpose and safety warning, which makes it minimally usable. Given that this is a destructive promotion tool with no annotations and no output schema, it would benefit from more context about what happens after promotion, when to prefer it over related tools, and whether the operation is reversible.
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 the parameters current, candidate, comment, and human_confirmed are already fully documented. The description only repeats the human_confirmed requirement without adding syntax, ordering, relationships, or additional meaning, meeting the baseline but not exceeding it.
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 clearly states the action: '晋升 candidate 为 current' (promote candidate to current), naming both the action and the resources involved. It also flags the operation as destructive, but it does not explicitly differentiate itself from sibling tools such as run_ab_test or snapshot_restore.
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 description provides an execution requirement ('必须 human_confirmed:true') but no guidance on when to use this tool versus related alternatives like run_ab_test or snapshot_restore. There are no usage contexts, prerequisites, or exclusion criteria beyond the confirmation requirement.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.