Skip to main content
Glama

发问并等人回答(会阻塞)

feishu_ask

Send a Feishu card question with option buttons and block until the human replies, returning their answer or a timeout flag when a decision or missing parameter is needed.

Instructions

在飞书里发一张带选项的卡片问一个问题,然后等人回答,把答案拿回来。用在真的缺关键信息、又没法自己查的时候:要用户拍板方案、要一个他没写在文档里的参数、要确认某个动作要不要执行。⚠️ 这个调用会阻塞(默认 120 秒,最多 600 秒),期间什么都做不了,所以不要滥用,一次任务最多问一两个问题;能靠 feishu_recent 从上下文里读出来的、能自己查到的、能用合理默认值继续的,都不要问。回答来源有两条:①点卡片上的选项按钮(需要网关在跑,毫秒级返回);②对方直接打字回一句。两条都走不通才会超时。返回 answered=true 时 text 就是对方的原话;answered=false 表示超时(不是报错),此时应当按默认方案继续或换个问法,不要反复重试。

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "question": "<question>"
    },
    "name": "feishu_ask"
  }
}

Input Schema

NameRequiredDescriptionDefault
chat_idNo发到哪个会话(oc_ 开头)。不填用默认会话。
optionsNo建议选项(最多 5 个,多余的截断),会渲染成按钮。网关在跑时点按钮就是答案;网关不在时按钮只是提示,对方要打字回。
questionYes要问的一句话问题。写清「需要他决定什么」,别问开放式的为什么。
timeout_secondsNo最多等多少秒,默认 120,最小 10,最大 600。
poll_interval_secondsNo轮询间隔秒数,默认 3,最小 1。间隔太小会白烧接口配额。

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.1

TDQS

A4.6/5.0
Behavior4/5

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

Goes well beyond the sparse annotations (readOnlyHint=false, openWorldHint=true) by disclosing the blocking cost (120s default, 600s max), the two answer paths (card buttons requiring a running gateway vs. typed reply), what a timeout means, and that answered=false is not an error and should not be retried. If it had also stated any permission or session prerequisites, it would earn a 5.

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 blocking warning, the when-to-use rule, and the return semantics are front-loaded and each sentence earns its place. The bold emphasis and repeated warnings like '不要滥用' and '不要反复重试' make it slightly longer than strictly necessary, but nothing is redundant in substance.

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?

No output schema exists, but the description explains the return shape itself (answered=true means the reply text is the user's words; answered=false means a timeout, not an error), including what to do after a timeout. Combined with the blocking and gateway notes, that is enough for an agent to call the tool correctly and to handle the result.

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 baseline is 3, but the description adds meaning the schema does not: options only function as answers when the gateway is running (otherwise they are just hints), and the blocking tradeoff tied to timeout_seconds. It also reinforces that a vague question is the wrong input ('写清需要他决定什么').

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?

States a concrete verb and resource: send a card with options into Feishu to ask a question, wait for the answer, and return it. It explicitly scopes itself against feishu_recent ('能靠 feishu_recent 从上下文里读出来的…都不要问'), so an agent can distinguish it from the messaging siblings without opening the schema.

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?

Gives explicit when-to-use conditions (missing critical info that can't be self-looked-up, needing a decision, an undocumented parameter, or action confirmation) and explicit when-not conditions with a named alternative (feishu_recent, self-lookup, reasonable defaults). It also caps usage ('一次任务最多问一两个问题'), which is real guidance about invocation frequency.

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