Trigger a quality optimization loop for AI agent outputs, or query results of an ongoing refinement cycle. Specify the agent and task to apply team quality rules.
Refine 质量优化循环——针对 Agent 产出做质量优化。
| Name | Required | Description | Default |
|---|---|---|---|
| task | No | 任务描述（trigger 时必填——Refine 针对哪个产出） | |
| action | Yes | 操作类型：trigger=触发质量循环 / query=查询结果 | |
| team_id | No | 团队 ID（可选——加载团队质量规则） | |
| agent_id | No | 目标 Agent 身份码（trigger 时必填） |
Changes observed during successful MCP inspections.
v0.1.0Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description must disclose behavioral traits, but it only says 'quality optimization loop' without explaining side effects, whether the operation is asynchronous, whether it mutates agent behavior, or what the loop actually does. Some behavioral context is implied by 'loop', but it is far from sufficient.
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 sentence, front-loaded, and contains no filler. However, it repeats the notion of 'quality optimization' ('质量优化循环' and '质量优化'), which slightly reduces precision while remaining concise overall.
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 tool has 4 parameters, no annotations, and no output schema, so the description carries heavy responsibility. It does not clarify what the trigger action produces, what query returns, whether results are persisted, or how the optimization loop behaves. Agents would struggle to know what to expect after invoking this tool.
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 each parameter already has a meaningful description. The tool description adds little beyond the concept of targeting 'Agent 产出', which is already reflected in the task and agent_id parameter descriptions. This aligns with the baseline of 3.
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 states a clear action ('质量优化' quality optimization) and resource ('Agent 产出' agent output), and identifies the tool as a 'loop', suggesting an iterative quality cycle. It is reasonably distinct from siblings like evaluate_output and optimize_skill, though it does not explicitly differentiate itself.
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 gives a general purpose but no explicit guidance on when to use this tool versus alternatives such as evaluate_output, evaluate, or optimize_skill. The trigger/query action semantics are only visible in the schema, not in the description, so the agent gets no usage context or exclusion criteria.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.