Evaluate agent output quality using a golden set, returning a score and failed cases. Identify underperforming responses to guide corrective action.
用 golden set 评估 Agent 产出质量，返回评分 + 失败用例。
| Name | Required | Description | Default |
|---|---|---|---|
| verbose | No | 是否输出详细报告 | |
| golden_set_path | No | golden set 文件路径（默认使用内置 golden set） |
Changes observed during successful MCP inspections.
v0.1.0Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description must carry the behavioral burden. It discloses that the tool performs an evaluation against a golden set and returns a score plus failure cases, which conveys its non-mutating character reasonably well. However, it does not describe output format, side-effect guarantees, or failure-case structure.
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 concise sentence that front-loads the core purpose and the expected result. Every word contributes meaning, with no filler or redundant restatement of the tool name.
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 simple tool with two optional parameters and no output schema, the description gives a reasonable high-level overview of inputs and outputs. It is not fully complete because it omits usage differentiation from sibling evaluation tools and does not clarify the return format, but it remains functional for a low-complexity 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 the schema already documents the two optional parameters clearly. The description does not add parameter-level detail, but the baseline of 3 is appropriate since it does not need to compensate for schema gaps.
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?
Description states a specific action—evaluating Agent output quality using a golden set—and names the key returned artifacts (score and failure cases). It is clear enough to distinguish the tool from most siblings, though it does not explicitly contrast it with similarly named evaluate or eval_suite.
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?
No guidance is given on when this tool should be used instead of evaluate, eval_suite, or run_audit. The intended context is implied by the golden-set mention, but without explicit alternatives or exclusion conditions, an agent cannot reliably choose between overlapping evaluation tools.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.