Skip to main content
Glama
mybolide

MCP Probe Kit

by mybolide
OverviewSchemaRelated ServersScoreDiscussions
TypeScript
Local

workflow

Read-onlyIdempotent

Guides the Agent in selecting the correct MCP tool by providing tool selection rules and a quick reference table. Supports explicit scenarios for deterministic workflow steps when the intent is clear.

Instructions

仅当 Agent 阅读 Skill 和各工具 description 后仍不确定该调用哪个 MCP 时使用的兜底选择指南。workflow 不做自然语言意图识别：scenario=auto（默认）只返回工具选择规则与速查表，不从 intent 猜 firstTool；Agent 根据完整对话自行判断或澄清。若 Agent 已明确场景，可传显式 scenario 获取该场景的确定性 firstTool、phases 和参数提示。同时确保用户项目已存在 .agents/skills/mcp-probe-kit/SKILL.md 与 AGENTS.md 中的 Skill 引用（缺失则自动创建/更新）。

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
intentNo可选上下文摘要。scenario=auto 时仅供指南展示，不参与自动分类；显式 scenario 时用于生成该场景的参数提示和阶段说明。
scenarioNo可选：显式场景。默认 auto 只返回 Agent 工具选择指南，不从 intent 推断场景；Agent 已确定场景时传 feature/bugfix/ui/... 获取确定性流程说明
project_rootNo可选。项目根目录绝对路径；未传时自动从 MCP 客户端工作区解析（如 Cursor 注入 WORKSPACE_FOLDER_PATHS、OpenCode/客户端配置的 cwd 等）。仅边缘场景需手动传入。

Schema Changelog

Changes observed during successful MCP inspections. Dates show when Glama detected each change.

  1. Changed3 schema fields changedv4.0.0
    • changedInput schema / properties / intent / description
      Previous value: -"用户目标或任务描述（自然语言）"New value: +"可选上下文摘要。scenario=auto 时仅供指南展示，不参与自动分类；显式 scenario 时用于生成该场景的参数提示和阶段说明。"
    • changedInput schema / properties / scenario / description
      Previous value: -"可选：显式场景；默认 auto 从 intent 推断"New value: +"可选：显式场景。默认 auto 只返回 Agent 工具选择指南，不从 intent 推断场景；Agent 已确定场景时传 feature/bugfix/ui/... 获取确定性流程说明"
    • changedInput schema / properties / scenario / enum
      Previous value: -[
-  "auto",
-  "feature",
-  "bugfix",
-  "ui",
-  "explore",
-  "commit",
-  "review",
-  "refactor",
-  "onboard",
-  "spec",
-  "memory"
-]New value: +[
+  "auto",
+  "feature",
+  "bugfix",
+  "ui",
+  "product",
+  "ralph",
+  "architecture",
+  "arch",
+  "explore",
+  "commit",
+  "work_report",
+  "report",
+  "test",
+  "review",
+  "refactor",
+  "onboard",
+  "spec",
+  "memory"
+]
  2. Changed1 schema field changedv3.7.0
    • addedInput schema / properties / project_root
      Added value: +{
+  "description": "可选。项目根目录绝对路径；未传时自动从 MCP 客户端工作区解析（如 Cursor 注入 WORKSPACE_FOLDER_PATHS、OpenCode/客户端配置的 cwd 等）。仅边缘场景需手动传入。",
+  "type": "string"
+}
  3. Addedv3.6.3

TDQS

A4/5.0
Behavior1/5

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

The description states the tool '确保用户项目已存在 .agents/skills/mcp-probe-kit/SKILL.md 与 AGENTS.md 中的 Skill 引用（缺失则自动创建/更新）' which implies file creation/update side-effects. This contradicts the annotation 'readOnlyHint: true' which indicates no state mutation. This is a serious contradiction, scoring 1 per the rubric.

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?

Three sentences in Chinese, front-loaded with the tool's purpose. Each sentence adds essential information: usage condition, behavior distinction, alternative usage, and side-effect. No wasted words; compact yet complete.

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?

Given the large set of sibling tools (23), the description covers the core use case (routing guidance) and parameter behavior. It mentions return types (table, deterministic flow, parameter hints) but lacks explicit output format details. With no output schema, a bit more specificity on the response structure would improve completeness. Otherwise adequate.

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?

Schema coverage is 100% with clear descriptions. The description adds behavioral meaning beyond the schema: it explains that 'intent' is only for display when scenario=auto and not used for classification, and that 'scenario' controls whether to return a table or deterministic flow. This enhances usability beyond the raw enum values.

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 clearly defines the tool as a fallback guidance when unsure which MCP to use. It distinguishes itself from sibling tools (which are direct task tools) by stating it returns a tool selection table or deterministic flow, not performing intent recognition itself. The verb '兜底选择指南' (fallback selection guide) is specific and differentiated.

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

Usage Guidelines5/5

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

Explicitly states when to use: only after reading Skill and tool descriptions when still uncertain. Also provides when-not: '不做自然语言意图识别' (does not do NLU) and that the agent should judge or clarify. Describes alternative scenarios: use explicit scenario for deterministic flow. Clear boundary conditions.

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

Install Server

Other Tools

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/mybolide/mcp-probe-kit'

If you have feedback or need assistance with the MCP directory API, please join our Discord server