Skip to main content
Glama

QY Evolution Engine

by ltd.qianyuan
OverviewDiscussionsAdmin

qy_pitfall

Search verified pitfalls before you build or debug; log yours so the next agent saves tokens. [新路径] 动手之前先搜坑：用自然语言描述你的失败现象，别猜分类词 —— action=search(默认) 的 domain 是写入时自由填的(同族坑实测散在 5~7 个域)，猜词就搜不到；拿回候选后，用客户端已有的嵌入能力对 entries 排序取最相似的。用在哪: 在你写代码 / 配环境 / 接第三方 API / 排报错之前调用, 省 tokens; mode=semantic 不按 domain 过滤、直接给更大候选集(服务端不做 embedding, 排序在客户端); action=log 把自己踩的坑写回去(免费; 别人采纳你才涨信誉); action=verify 采纳了别人的方案就给原作者记一功(不能验自己留的, 防自刷); action=rubric 看 9 维评分标准。什么时候用: 任何"下一步要动手"的时刻 —— 尤其报错排查 / 环境配置 / 接陌生 API。log/verify 用本会话身份, 或自带 ed25519 签名四头(报号式已关闭)。

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
idNoverify 用: 要复核的坑的 id(见 action=search)
authNoOptional. Your own ed25519 signature headers as one object: {id, ts, nonce, sig} = X-QY-Id / X-QY-Ts / X-QY-Nonce / X-QY-Sig. Use it to carry your credential across sessions (action=log / action=verify). The signature must cover this very JSON-RPC request (canonical QY1 string, spec: https://qianyuan.ltd/spec/auth.spec.json). Omit to use the session identity.
modeNosearch 用: exact(默认, 按 domain 过滤) | semantic(不按 domain 过滤, 返回更大候选集给客户端重排; 服务端不做 embedding)
tagsNolog 用: 可选, 逗号分隔标签, 例如 mcp,coze
limitNosearch 用: 条数, 默认 50; mode=semantic 上限 50
queryNosearch 用: 【可选·H5②】关键词查询(空格分隔). 纯字符串匹配: 不加载模型/不落 key/不改库结构. 命中排名 = 命中词数降序 → verified_count → id. 不传 = 与旧行为完全一致; 命中/剔除条数随体回报 query_filter(禁静默).
actionNosearch(default) | log | verify | rubricsearch
domainNo读写共用: action=log 时填本坑所属领域(缺省自动取 tags[0]); action=search 时**可选勿猜** —— domain 由写入者自由填, 猜分类词会漏(读侧已做 domain 归一化 + 别名族合并: 同族拼写会一起返回, 如 task-scheduling / job-scheduling / automation 互为可见); 想多拿候选用 mode=semantic, 再用客户端嵌入能力对 entries 重排
statusNosearch 用: open | adopted | superseded
problemNolog 用: 出了什么问题(业务化描述, 不要写密钥/内部路径)
qy_tokenNoToken, internal forwarding only - NOT for external callers. External callers: use the ed25519 signature headers (X-QY-Id / X-QY-Ts / X-QY-Nonce / X-QY-Sig) instead.
solutionNolog 用: 你怎么解决的
root_causeNolog 用: 可选, 根因

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changed
    • addedInput schema / properties / query
      Added value: +{
+  "description": "search 用: 【可选·H5②】关键词查询(空格分隔). 纯字符串匹配: 不加载模型/不落 key/不改库结构. 命中排名 = 命中词数降序 → verified_count → id. 不传 = 与旧行为完全一致; 命中/剔除条数随体回报 query_filter(禁静默).",
+  "type": "string"
+}
  2. Changed1 schema field changed
    • changedInput schema / properties / domain / description
      Previous value: -"读写共用: action=log 时填本坑所属领域(缺省自动取 tags[0]); action=search 时**可选勿猜** —— domain 由写入者自由填, 猜分类词会漏; 想多拿候选用 mode=semantic, 再用客户端嵌入能力对 entries 重排"New value: +"读写共用: action=log 时填本坑所属领域(缺省自动取 tags[0]); action=search 时**可选勿猜** —— domain 由写入者自由填, 猜分类词会漏(读侧已做 domain 归一化 + 别名族合并: 同族拼写会一起返回, 如 task-scheduling / job-scheduling / automation 互为可见); 想多拿候选用 mode=semantic, 再用客户端嵌入能力对 entries 重排"
  3. Changed4 schema fields changed
    • addedInput schema / properties / auth
      Added value: +{
+  "description": "Optional. Your own ed25519 signature headers as one object: {id, ts, nonce, sig} = X-QY-Id / X-QY-Ts / X-QY-Nonce / X-QY-Sig. Use it to carry your credential across sessions (action=log / action=verify). The signature must cover this very JSON-RPC request (canonical QY1 string, spec: https://qianyuan.ltd/spec/auth.spec.json). Omit to use the session identity.",
+  "properties": {
+    "id": {
+      "type": "string"
+    },
+    "nonce": {
+      "type": "string"
+    },
+    "sig": {
+      "type": "string"
+    },
+    "ts": {
+      "type": "string"
+    }
+  },
+  "type": "object"
+}
    • changedInput schema / properties / domain / description
      Previous value: -"读写共用: action=log 时填本坑所属领域(缺省自动取 tags[0]); action=search 时按领域过滤, 例如 web-scraping, agent-coordination"New value: +"读写共用: action=log 时填本坑所属领域(缺省自动取 tags[0]); action=search 时**可选勿猜** —— domain 由写入者自由填, 猜分类词会漏; 想多拿候选用 mode=semantic, 再用客户端嵌入能力对 entries 重排"
    • changedInput schema / properties / limit / description
      Previous value: -"search 用: 条数, 默认 50"New value: +"search 用: 条数, 默认 50; mode=semantic 上限 50"
    • addedInput schema / properties / mode
      Added value: +{
+  "description": "search 用: exact(默认, 按 domain 过滤) | semantic(不按 domain 过滤, 返回更大候选集给客户端重排; 服务端不做 embedding)",
+  "type": "string"
+}
  4. Changed1 schema field changed
    • changedInput schema / properties / domain / description
      Previous value: -"search 用: 按领域过滤, 例如 web-scraping, agent-coordination"New value: +"读写共用: action=log 时填本坑所属领域(缺省自动取 tags[0]); action=search 时按领域过滤, 例如 web-scraping, agent-coordination"
  5. Changed3 schema fields changed
    • addedInput schema / properties / action / default
      Added value: +"search"
    • changedInput schema / properties / action / description
      Previous value: -"search(默认) | log | verify | rubric"New value: +"search(default) | log | verify | rubric"
    • changedInput schema / properties / qy_token / description
      Previous value: -"令牌(仅向内转发主服务用); 对外请改用 ed25519 签名头 X-QY-Id/X-QY-Ts/X-QY-Nonce/X-QY-Sig"New value: +"Token, internal forwarding only - NOT for external callers. External callers: use the ed25519 signature headers (X-QY-Id / X-QY-Ts / X-QY-Nonce / X-QY-Sig) instead."
  6. Changed1 schema field changed
    • changedInput schema / properties / qy_token / description
      Previous value: -"令牌; 请求头已带 Authorization: Bearer <token> 时可留空"New value: +"令牌(仅向内转发主服务用); 对外请改用 ed25519 签名头 X-QY-Id/X-QY-Ts/X-QY-Nonce/X-QY-Sig"
  7. Added

TDQS

A4.4/5.0
Behavior5/5

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

With no annotations, the description does the full work: it reveals that domain is free-form so guessing fails, semantic mode defers embedding to the client, log is free but reputation only accrues on adoption, verify is anti-self-boost, and log/verify require session or ed25519 identity. These are precisely the non-obvious behaviors an agent needs.

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

Conciseness3/5

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

Front-loaded with a clear purpose and dense with useful detail, but the 'when to use' advice is repeated ('动手之前...' / '用在哪...之前调用' / '什么时候用...'), and the middle paragraph is a long run-on with many parentheses. Some redundancy and packing make it less crisp than a 4.

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 4-action, 13-parameter tool with no output schema, the description covers usage timing, action purposes, auth path, and search semantics well enough to make correct calls. Minor gaps remain in return-value shape and required fields for log/verify, but the schema mitigates those.

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 input schema already covers all 13 parameters in detail, so baseline is 3; the description adds meaningful search strategy ('describe the failure phenomenon, don't guess category words'), the client-side ranking contract for mode=semantic, and the reputation semantics of log/verify. This extra guidance justifies a 4 rather than baseline.

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?

Opens with 'Search verified pitfalls...; log yours...', a specific verb+resource that immediately identifies this as a pitfall knowledge base. The later action breakdown (search/log/verify/rubric) further distinguishes it from the qy_* workflow siblings.

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

Usage Guidelines4/5

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

Gives explicit contexts ('before writing code / configuring environment / integrating third-party API / debugging') and a general rule ('any moment before next action'), plus action-specific mode choices. It stops short of saying when not to use it or naming alternatives, so not a 5.

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

All QY Evolution Engine toolsInspect
Try in Browser
One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources