Skip to main content
Glama

独行录 / opcmenu

我的定位(阶段台阶 + 六维 + 任务)

get_my_positioning

【需要登录】【何时用】用户问「我现在到哪一步了」「接下来该干嘛」「帮我把这周能做的都做了」。返回阶段台阶(主线五级 + 融资阶段)上的当前等级、六维画像、称号与总分,以及全部任务的完成态与 nextUp(最该做的三件事)。

【组合链·代办】nextUp 里每条任务都带 suggestedTool——这是 agent 面相对 App 的关键差别:App 的 CTA 只能把人跳到那一屏让他自己动手,你能直接把这件事做完。 对照表: · 写「我能提供什么」/ 一句话说清项目 → update_my_profile(canOffer)(partner.can_offer 与 funding.one_liner 两条任务判的就是 User.canOffer 的字数,分别 ≥30 / ≥20 字,写虚了过不了) · 融资资料、轮次金额、传 BP → set_my_role_profile(fundraising) · 邀请同行 → get_my_invite · 发需求(招兼职 / 找合伙人 / 找资源)→ create_need · 发布产品 → create_product · 归位产业链 → set_my_chain_position · 看看我的名片长什么样 → get_my_card;去回消息 → list_my_conversations 用户说「把这周能做的都做了」就真的一条条做完再汇报,别只念清单。

【口径/坑】 · 本工具会刷新你的定位快照(写 PositioningState:算分快照 + auto 任务的完成戳),所以它不是纯读工具,别当免费接口循环调。只想看个大概用 get_my_brief。 · level.source='declared'(用户自报)永远优先于 inferred(LLM 读证据判的)/ observed(确定性兜底)。要改自报值走 set_my_role_profile(venture.stage)。 · basis / signals / confidence 是 LLM 给的判词,转述它,别自己另判一个等级,更别说「我觉得你其实已经到 XX 了」。 · 任务只增不减:达标那刻盖戳,之后数据回落也不打回未完成(用户不会莫名其妙掉级)。 · 默认裁掉全部任务的培训正文(guide),否则一次调用几万 token。要正文:includeGuides=true + taskKeys 指定 1~5 条(「证照与备案那几项怎么办」就一次要 5 条,别发 5 次往返)。 · defaultSection 是服务端按段位给的分流建议:'chain'=这人该先去归位产业链(list_my_chain_anchors / set_my_chain_position),'self'=先补自我定位。别自己另判一套。 · 任务带 group(如「证照与备案」),这一组的进度直接读返回体的 compliance{group,total,done},别自己数也别手抄条数。 · verify='manual' 的任务平台观测不到,要用 mark_positioning_task 自报打勾(一次可以打一批)。

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
taskKeysNo只看这几条任务(1~5 条;配合 includeGuides 取它们的培训正文)
includeGuidesNo是否带回培训正文 guide,默认 false。设 true 时**必须同时给 taskKeys**;正文只出现在返回体的 tasks[] 里,tracks 里不重复一份

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed3 schema fields changed
    • changedInput schema / properties / includeGuides / description
      Previous value: -"是否带回培训正文 guide,默认 false。设 true 时**必须同时给 taskKey**,且只返回那一条的正文"New value: +"是否带回培训正文 guide,默认 false。设 true 时**必须同时给 taskKeys**;正文只出现在返回体的 tasks[] 里,tracks 里不重复一份"
    • removedInput schema / properties / taskKey
      Removed value: -{
      -  "description": "只看某一条任务(配合 includeGuides 取它的培训正文)",
      -  "maxLength": 60,
      -  "type": "string"
      -}
    • addedInput schema / properties / taskKeys
      Added value: +{
      +  "description": "只看这几条任务(1~5 条;配合 includeGuides 取它们的培训正文)",
      +  "items": {
      +    "maxLength": 60,
      +    "type": "string"
      +  },
      +  "maxItems": 5,
      +  "minItems": 1,
      +  "type": "array"
      +}
  2. First observed

TDQS

A5/5.0
Behavior5/5

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

Annotations only declare readOnlyHint=false and idempotentHint=false, but the description goes much further by disclosing the side effect: it writes a PositioningState snapshot and auto-task completion timestamps. It also documents monotonic task completion, guide truncation for token economy, defaultSection semantics, and manual verification via mark_positioning_task—all behaviors beyond what annotations convey.

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 description is long but tightly organized into action-oriented sections: when to use, suggested-tool mapping, and pitfalls. Every block carries operational instructions an agent needs, and the mapping table is dense with no filler.

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 to lean on, the description compensates fully: it covers return fields, side effects, level.source precedence, basis/signals/confidence handling, compliance group structure, defaultSection meanings, and verify='manual' behavior. An agent has enough context to invoke the tool correctly and interpret its results.

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

Parameters5/5

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

Schema coverage is already 100%, but the description adds important coupling rules: includeGuides=true requires taskKeys, guides appear only in tasks[] and not tracks, and the default is false to avoid tens of thousands of tokens. It even gives a concrete usage pattern (request all 5 guides at once for '证照与备案' instead of making 5 round trips).

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 opens with explicit trigger phrases ('我现在到哪一步了', '接下来该干嘛') and enumerates exactly what is returned: stage level, six-dimension profile, title, total score, task completion states, and nextUp. It also distinguishes the tool from get_my_brief, so an agent can tell them apart immediately.

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?

A dedicated '何时用' section states when to call the tool, and a warning explains when not to: it refreshes the positioning snapshot, so it should not be looped as a free read endpoint. The suggestedTool mapping further routes the agent to update_my_profile, set_my_role_profile, create_need, create_product, and other siblings for actually completing each nextUp item.

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