Skip to main content
Glama

独行录 / opcmenu

我的今日全景

get_my_brief
Idempotent

【需要登录】【何时用】任何「今天怎么样 / 有什么要处理的 / 日报 / 早上问一句」的场景都从这里开始。它把 App 里分散在八屏、且必须由用户自己想起来去点的八件事并成一次返回: ① 未读私信数 ② 最近 7 天谁看过我(计数 + 具名前几位)③ 今日开聊额度 ④ 7 天内截止且我还没报的场次 ⑤ 定位栏「最该做的三件事」⑥ 我办的活动待审报名数 ⑦ 产业链归位现状(几个锚点、几个还没归位)⑧ 等我回应的合作请求数。 这是 agent 面独有的形态——App 里没有、也不该有这一屏;一次调用换一段话。

【组合链】 · unread>0 → list_my_conversations 找出是谁 → read_messages 看内容 → send_message 回。 · attention.top[].viewerId → get_creator 看他是谁 → start_conversation 主动开聊(这是全站转化最高的一条链)。 · deadlines[].slug → get_signup_activity 看要填什么 → submit_signup 报名。 · positioning.nextUp[].suggestedTool 就是「这件事该调哪个工具」,用户说「把这周能做的都做了」就照着一条条真做完再汇报。 · organizer.activities[].slug → 去主办方那条链审报名。 · chain.unplacedCount>0 → 念出 chain.unplaced[] 里那几个名字 → 逐个 set_my_chain_position 补齐(要看每个锚点的链位原文先 list_my_chain_anchors)。 · cooperation.awaitingMyReply>0 → cooperation.top[] 里就是谁在等 → get_cooperation_request 读全文 → respond_cooperation_request(要全量清单去 list_my_cooperation_requests)。 · 合作目标、合作任务与目标邀请不在这八路里(那是另一套),用 get_my_work;安排路径与结果反馈用 get_my_dispatch(该读取会标记建议已看,不要后台顺手调用)。 · chatQuota.remaining=0 时别再张罗开聊,先 get_my_invite(引荐一位完成入驻的同行 = 每天永久 +1 次)。

【口径/坑】 · 八路并发取,任何一路失败都降级成 null,整体永不失败。哪几路挂了写在 degraded[] 里——null ≠ 0,别把「取不到」说成「没有」。 · 未读数、额度、待审数都是实时推导的,没有重置任务;额度不会在白天自己回来。 · 具名访客只有真人登录后浏览才认得出;anonymous 那部分没有身份可查,是计数下限(按 ipHash 折叠),不许编人名。 · 报名 feed 服务端是「置顶优先、再按截止近的排」,这里已按截止时间重排并只留 7 天内、我还没报的。 · 不是纯只读:定位那一路走的是不落算分快照的算法,但没有新鲜阶段结论时会在后台排一次 LLM 阶段重判并写回结论。所以标了 readOnlyHint=false。代价有硬闸:结论 7 天新鲜期内不重判、同一人 10 分钟内只排一次、证据没变不重判——当日报天天调、定时调都不会放大成本,放心调。 · chain 只给名字和链位标题(摘要面);要 summary / 全部链位原文去 list_my_chain_anchors,要上下游才去 get_chain_anchor(那个真花钱)。 · cooperation 区分 awaitingMyReply(别人在等我)与 awaitingTheirReply(我在等别人)——催谁完全不同,别混成一个「有 N 条合作」;awaitingSecretaryRelay 是发给云用户、由独行录人工小秘书转达中的,对方不在站内,别说成在等 TA 回。 · 要完整任务清单(全部任务的完成态)用 get_my_positioning。

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault

No arguments

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.8/5.0
Behavior5/5

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

Goes well beyond annotations: requires login, degrades failing lanes to null and never fails, records failures in degraded[], stresses null != 0, explains real-time derivation with no reset, anonymous-count caveats, server-side reordering, and explicitly discloses that it is not purely read-only, justifying readOnlyHint=false and listing hard cost guards. This is rich behavioral context with no contradiction to annotations.

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

Conciseness4/5

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

The description is long but well-structured and front-loaded with login and when-to-use before the enumerated list, chains, and pitfalls. Every section earns its place given the eight data lanes and caveats, though a few rhetorical phrases (e.g., 'App 里没有、也不该有这一屏') could be trimmed for tighter conciseness.

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

Completeness5/5

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

With no output schema, the description still enumerates all eight return elements, their relevant fields, failure/degradation semantics, freshness and quota behavior, authentication, cost implications, and routing to sibling tools. An agent has enough to call it correctly, interpret the response, and decide next actions without additional context.

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?

Input schema is empty with 100% coverage, so there are no parameters the description must explain; baseline for 0 params is 4. It adds incidental semantics for output fields (unread, attention.top[], deadlines[].slug, positioning.nextUp[], cooperation.top[]), which helps result interpretation even though it is not input-parameter guidance.

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?

Description names the verb (get) and resource (今日全景/brief) and concretely enumerates the eight aggregated things it returns, so an agent knows exactly what it offers. It also distinguishes it from sibling tools (get_my_work, get_my_dispatch, get_my_positioning) and states this is an agent-only view not present in the app.

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 marks the entry conditions: any '今天怎么样/有什么要处理的/日报/早上问一句' scenario starts here. It names exclusions and alternatives: collaboration goals/tasks use get_my_work, dispatch paths/results use get_my_dispatch with a warning not to call it in the background, full task list uses get_my_positioning, and when chatQuota.remaining=0 to use get_my_invite.

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

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources