Skip to main content
Glama

独行录 / opcmenu

找人才(按职业找人,不是找产品)

list_talent
Read-onlyIdempotent

【何时用】用户要的是某一类人本人而不是某个产品/服务时用:「帮我找个能写代码的」「有没有做出海的人」「找几个律师/财税顾问聊聊」。和 list_service_products 的区别:那边是「他卖什么」(产品目录),这边是「他本人是干什么的」(人的目录);和 search_people 的区别:那边是语义搜,这边是结构化职业筛选,适合按类目扫一遍。

【组合链】items[].user.id → get_creator 看完整主页 → start_conversation 开聊(开聊走每日额度,撞 429 会直接返回「怎么办」的出口,别重试);user.id → follow_creator 先关注不打扰;items[].company.slug → get_company。人卡唯一动作就是进个人主页,没有别的落点。

【口径/坑】 · 职业(items[].professions)是机判闭集:由资料/名片/自述跑分类器写入,不是本人勾选;一人最多两个主职业。没被判出职业的人不进这个目录,想找他走 search_people。 · chip 是职业的合并桶(比如律师/财税/HR 都并在「咨询·顾问」里),卡片上的职业胶囊是细粒度标签,两者不是一回事。 · 此刻真正有人的 chip 用 get_talent_chips 查(服务端按真实人数 ≥ 阈值才下发,并带每个 chip 的人数);这里的枚举只是合法值集合,不代表此刻每个都有人。传了没下发的 chip 会拿到很少甚至 0 条,不是报错。不传 chip 或传 all = 全部;传不认识的 key 按全部处理(不 400)。 · 匿名只回真人(在册、已入驻、非测试号、非运营机构号);返回里没有手机/邮箱/外链,要联系只能开聊。 · 登录后,该 chip 下全部真人之后还会接上云用户(items[].user.isCloud=true:还没用 App 的社群成员,bio 是「职位 · 公司」,company.slug 为空=没有公司页)。云用户不能开聊,联系只能 send_cooperation_request,由独行录人工小秘书转达。 · 规模小(百级),分页是 offset(nextCursor 就是下一次的 offset)。

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
chipNo职业 chip,可选;不传或 all=全部。合法值:all / dev / creative / growth / consult / product / training / hardware / sales / global / health(dev=开发·技术,creative=内容·创意,growth=运营·增长,consult=咨询·顾问,product=产品,training=培训·教育,hardware=硬件·供应链,sales=销售·BD,global=出海·跨境,health=健康·心理)。此刻真正有人的那几个用 get_talent_chips 查(带人数)
limitNo返回条数,默认 20,最多 50
offsetNo偏移量,默认 0;用上一次返回的 nextCursor

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changed
    • changedInput schema / properties / chip / description
      Previous value: -"职业 chip,可选;不传或 all=全部。合法值:all / dev / creative / growth / consult / product / training / hardware / sales / global / health(dev=开发·技术,creative=内容·创意,growth=运营·增长,consult=咨询·顾问,product=产品,training=培训·教育,hardware=硬件·供应链,sales=销售·BD,global=出海·跨境,health=健康·心理)。此刻实际可用的 chip 以 GET /v1/talent/chips 为准"New value: +"职业 chip,可选;不传或 all=全部。合法值:all / dev / creative / growth / consult / product / training / hardware / sales / global / health(dev=开发·技术,creative=内容·创意,growth=运营·增长,consult=咨询·顾问,product=产品,training=培训·教育,hardware=硬件·供应链,sales=销售·BD,global=出海·跨境,health=健康·心理)。此刻真正有人的那几个用 get_talent_chips 查(带人数)"
  2. First observed

TDQS

A4.9/5.0
Behavior5/5

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

Beyond the readOnly/idempotent annotations, the description reveals essential behavioral quirks: professions are machine-classified and closed-set, chips are merged buckets whose live population must be checked via get_talent_chips, unknown chips silently fall back to 'all', anonymous mode returns only real users, and logged-in mode may include cloud users who cannot be chatted with. No contradiction with annotations.

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?

Though long, the description is tightly structured into scannable sections (when-to-use, combination chain, gotchas) and every sentence carries load-bearing information. The most decision-relevant purpose is front-loaded before the details.

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?

Despite having no output schema, the description covers the key item fields (user.id, company.slug, user.isCloud), visibility/auth differences, contact restrictions, pagination behavior, and non-error fallback behavior. This is sufficient for an agent to call the tool and interpret results correctly.

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%, so the baseline is 3; the description adds value by explaining chip bucket semantics, the dynamic availability of chips, and the fallback behavior for unknown values. It also clarifies that offset corresponds to the previous response's nextCursor.

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 a precise use case ('用户要的是某一类人本人...') and gives concrete examples, and it explicitly distinguishes itself from list_service_products and search_people. This makes the tool's role unambiguous relative to closely related siblings.

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?

It has a dedicated '何时用' section stating when to choose this tool and names the two alternatives with the conditions that select them. It also documents intended follow-up chains (get_creator, start_conversation, follow_creator, get_company), giving clear guidance on how to use the result.

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