Skip to main content
Glama

回归测试

test

Derive targeted regression scope from acceptance criteria and page impact, run checks on declared pages, and record traceable results; return unavailable rather than a false pass when no runner exists.

Instructions

派生测试范围并执行定向回归,写入 test-results.json。范围 = spec.json 的验收标准 ∪ changes.json 的页面级影响面(读取 .vibeguard/pages.json 声明页面入口);页面映射不完整时只扩大、不缩小(并入全部冒烟页);没有 Spec 时降级为通用冒烟测试。测试失败会沿页面证据链关联相关的 out-of-spec 变更。未配置下游 test 阶段工具时返回 status:"unavailable"(该阶段没有本地兜底),绝不伪装成通过。

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "test"
  }
}

Input Schema

NameRequiredDescriptionDefault

No arguments

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A4.2/5.0
Behavior4/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations, the description carries the full burden and does well: it discloses the side effect (writes test-results.json), the expand-only safety rule for incomplete page maps, the no-Spec fallback, and critically that it returns status:"unavailable" rather than faking a pass. Remaining gaps are minor — it doesn't state whether files other than test-results.json are touched or what permissions are needed.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The purpose and output artifact are front-loaded in the first clause, followed by scope rules, fallback behavior, and failure semantics in a logical order. Though dense, every clause introduces a distinct rule (union scope, expand-only, degraded mode, unavailable status) with no wasted sentences.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a complex, zero-parameter, no-output-schema tool, the description covers inputs, scope computation, degradation, failure linkage, and at least one return status. It stops short of describing the normal (non-unavailable) return shape or the structure of test-results.json, which is the main remaining gap given the absence of an output schema.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The tool takes zero parameters, so the baseline is 4. The description nevertheless clarifies that all inputs are implicit file reads (spec.json, changes.json, .vibeguard/pages.json), which helps the agent understand that no arguments are expected.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description names a specific verb pair (派生范围并执行定向回归) and a concrete resource (regression testing writing to test-results.json), and spells out the scope algebra (spec.json acceptance criteria ∪ changes.json page impact). An agent can tell this is the regression-execution stage tool, not clarify/health/review, without opening any schema.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines3/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Usage conditions are implied by the pipeline rules: it runs when a spec/changes exist, degrades to generic smoke test without a Spec, and returns unavailable when no downstream test tool is configured. However, there is no explicit 'use this instead of X when Y' routing against the sibling tools (clarify, review, health), so the agent must infer the stage from context.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Deploy Server

Other Tools