Skip to main content
Glama

原地更新已发出的卡片

feishu_update_card

Replace an existing Feishu card message in place to update progress or show results without sending a new chat bubble; use the original message_id from a card sent with update_multi enabled.

Instructions

把已发出的卡片整张替换成新内容,聊天里不新增消息气泡 —— 这是"不刷屏"的关键手段。典型用法:先发一张进度卡,之后反复 update 同一个 message_id 推进进度 / 换成结果卡。限制:只有发出时带 config.update_multi = true 的卡片才能更新,否则飞书会报错;也不能更新别人发的消息,只能用自己发出的 message_id。不适合:想让用户看到历史过程的每一步(每次都会覆盖,只留最新一版);需要保留每步记录就用 feishu_send_text 逐条追加。

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": {
      "message_id": "<message_id>",
      "card": "<card>"
    },
    "name": "feishu_update_card"
  }
}

Input Schema

NameRequiredDescriptionDefault
cardYes新的完整卡片 JSON(整张替换,不是补丁)。结构同 feishu_send_card;建议保留 config.update_multi = true 以便继续更新。
message_idYes要更新的卡片消息 id(om_ 开头),来自 feishu_send_card 的返回值,必须是本应用发的卡片消息。

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.1

TDQS

A4.6/5.0
Behavior5/5

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

Annotations only give readOnlyHint=false and openWorldHint=true; the description adds far more: the update overwrites the entire card (no patch semantics), no new message bubble appears, the operation fails if update_multi was not set at send time, and it cannot touch other people's messages. These are real failure modes and side-effect semantics the annotations do not 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 effect and the anti-spam rationale are front-loaded, followed by the typical workflow, then hard limits, then a when-not case. Every sentence carries a distinct piece of decision-relevant information with no filler.

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

Completeness4/5

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

For a 2-parameter mutation with a free-form nested card object and no output schema, the description covers preconditions, ownership, and overwrite semantics well. It does not say what the call returns (e.g., whether a new/refreshed message_id is produced), which an agent driving a repeated update loop might want, but that is the only notable gap.

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

Parameters3/5

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

Schema coverage is 100% and the schema already documents both message_id (om_ prefix, comes from feishu_send_card) and card (full replacement JSON, same structure as feishu_send_card). The description reinforces the "entire replacement, not a patch" and "preserve update_multi for further updates" points, but adds little beyond what the schema states, so the baseline 3 applies.

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?

"把已发出的卡片整张替换成新内容,聊天里不新增消息气泡" states a specific verb (整张替换) and resource (已发出的卡片) plus the observable effect that separates it from feishu_send_card. An agent can immediately tell this is an in-place mutation of an existing message rather than a new send.

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 spells out the canonical pattern (send a progress card, then repeatedly update the same message_id), names a hard precondition (config.update_multi = true or Feishu errors), names an ownership restriction (only your own message_id), and gives an explicit "不适合" case routed to feishu_send_text. When-to-use, when-not-to-use and an alternative are all present.

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