Skip to main content
Glama

独行录 / opcmenu

给定位任务打勾(线下动作自报)

mark_positioning_task
Idempotent

【需要登录】【何时用】用户完成了平台观测不到的线下动作:注册了公司、拿到商标 / 软著 / ICP 备案、收到第一笔钱、开始盈利……由他自报,平台不审核(可以顺手把备案号/注册号填进 note)。

【组合链】打完勾返回体自带涨分回执(打勾前后的总分与段位、本次新完成了哪些任务)——直接念给用户,别再调 get_my_positioning 前后各拉一次自己减。段位变了就顺势给下一步:get_my_positioning 看新一级的任务,或按 nextUp 的 suggestedTool 直接接着做。

【口径/坑】 · 只有 manual 类任务能打勾,auto 类(发产品、聊过多少人、发过几条需求)是平台记录算出来的,硬打会 400 task_not_manual——那不是 bug,是防止分数变成自助填空。 · 合法 taskKey(从服务层的 manual 任务集合生成):build.company(公司注册) | build.trademark(商标注册) | build.copyright(软件著作权登记) | build.copyright_ec(电子软著(电子证书)) | build.icp(ICP 备案) | build.police(公安备案) | build.app_filing(App 备案) | build.mp_filing(小程序备案) | build.llm_filing(大模型 / 算法备案) | build.security_assessment(互联网信息服务安全评估) | build.patent(专利申请) | revenue.first_pay(拿到第一笔收入) | revenue.repeat(有第二个不认识的付费客户) | profit.covered(收入覆盖成本) | growth.ad_basics(学会:一条广告只干一件事) · done=false 是取消打勾(连 note 一起删)。 · 不做任何审核校验:note 就是个备忘,填错也只影响他自己。别拦着用户填。

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
doneNotrue=打勾(默认),false=取消打勾
noteNo备忘,比如备案号 / 注册号,可选
taskKeyYes要打勾的任务 key。合法值:build.company(公司注册) | build.trademark(商标注册) | build.copyright(软件著作权登记) | build.copyright_ec(电子软著(电子证书)) | build.icp(ICP 备案) | build.police(公安备案) | build.app_filing(App 备案) | build.mp_filing(小程序备案) | build.llm_filing(大模型 / 算法备案) | build.security_assessment(互联网信息服务安全评估) | build.patent(专利申请) | revenue.first_pay(拿到第一笔收入) | revenue.repeat(有第二个不认识的付费客户) | profit.covered(收入覆盖成本) | growth.ad_basics(学会:一条广告只干一件事)

Schema Changelog

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

  1. First observed

TDQS

A4.9/5.0
Behavior5/5

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

Annotations already indicate a mutating, idempotent, non-read-only operation. The description adds meaningful behavioral context: login is required, the platform performs no audit or validation, note is only a memo, done=false deletes the note, illegal manual-task keys produce a specific 400 error, and the response carries a score receipt. These details go well beyond the annotations, and there is no contradiction.

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 with clear sections: login, when to use, combination-chain behavior, and pitfalls. Every sentence carries operational value—there is no filler. The duplicated taskKey list is acceptable because it is embedded with the rule that only manual tasks are legal.

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?

Even without an output schema, the description covers the return behavior (score receipt with before/after totals, rank, newly completed tasks), the error mode (400 task_not_manual), authentication, cancellation semantics, and follow-up routing. For a state-changing tool with edge cases, this is a complete and self-sufficient definition.

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 description coverage is 100%, so the schema already documents all three parameters. The description adds value by explaining semantics not obvious from the schema alone: the default for done is true, false cancels and deletes the note, note should not block the user because it is never validated, and taskKey must come from the manual-task set. The taskKey list is partially redundant with the schema but is wrapped in the manual-only rule.

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 states a specific verb and resource: the user self-reports offline actions to check off positioning tasks (给定位任务打勾). It distinguishes this tool from sibling tools by clarifying that only manual tasks can be marked, while auto tasks are computed by the platform. It also references get_my_positioning as the read-side counterpart, so an agent can tell them apart.

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?

The description explicitly says 'when to use' with concrete triggers: user completed actions invisible to the platform such as company registration, trademark, ICP filing, first revenue, profitability. It also gives clear exclusions: auto tasks cannot be checked and will return 400 task_not_manual; done=false means cancel and deletes the note. It tells the agent not to re-fetch get_my_positioning before/after and instead use the returned receipt or nextUp.suggestedTool.

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.

TDQS

A4.1/5.0
Disambiguation4/5

Each tool has a clearly documented purpose, often with explicit 'when to use' guidance and cross-references, making the vast majority easy to tell apart. A few clusters (get_my_brief, get_my_positioning, get_my_work, get_my_dispatch) and data-overlapping get_my_card vs get_my_profile require careful reading, but descriptions are detailed enough to prevent serious misselection.

Naming Consistency4/5

The overwhelming majority follow snake_case verb_noun conventions (create_product, update_need, list_my_signups). Minor deviations include noun-only feed names (personalized_feed, random_feed), inconsistency between 'prefs' and 'preferences' in notification tools, and a mix of update_* and set_* for mutations, but the pattern remains predictable overall.

Tool Count1/5

137 tools is an extreme mismatch for any MCP server, far exceeding the 50+ threshold for a score of 1. Even with a broad multi-domain platform, this volume makes tool selection and navigation impractical and heavily burdens the agent's context window.

Completeness5/5

The surface covers full lifecycles for needs, products, activities/signups, conversations, collaboration goals/tasks, dispatch, profile/onboarding, and supporting resources like companies, parks, policies, and ratings. Deliberate omissions (no user-post creation, no organizer profile editing via agent) are explicitly documented, so core workflows have no obvious dead ends.

Resources