Skip to main content
Glama

撤回一条消息

feishu_recall
Destructive

Recall messages your bot sent within the past 24 hours, and remove files attached to them. Only self-sent messages can be recalled under Feishu rules.

Instructions

撤回机器人自己发出去的消息(飞书只允许撤回 24 小时内的、且只能撤回自己发的)。也用于「删掉群里那个旧文件」——文件是挂在消息上的,删了消息文件就一起没了。不是自己发的消息会失败,这不是权限问题而是飞书规则。

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>"
    },
    "name": "feishu_recall"
  }
}

Input Schema

NameRequiredDescriptionDefault
message_idYes要撤回的消息 id(om_ 开头)。

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 already declare that this is a destructive, non-read-only operation, and the description adds context that the annotations do not cover: a 24-hour window, a self-sent-only restriction, and the cascading destruction of attached files. It also explains that failures for messages not sent by the bot are caused by Feishu's rules, not by permissions, which prevents the agent from misreading an error.

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 description is three tight sentences, and the scope limits are front-loaded before the file-deletion use case. It repeats the self-sent rule twice (once in the parenthetical and once in the failure sentence), but the repetition serves the different purpose of explaining error semantics.

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?

For a single-parameter destructive tool with annotations, the description covers eligibility rules, the side effects, the failure mode, and the file-deletion workaround. No output schema exists, so return values need not be explained.

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?

The single parameter is fully documented in the schema, so the baseline is 3. The description adds value by constraining the acceptable values: the message must have been sent by the bot and must be less than 24 hours old. This is validity semantics the schema does not encode.

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 (recalling a message the bot itself sent) and makes the scope explicit up front: only messages sent by the bot and only within 24 hours. It also distinguishes this tool from file-deletion siblings by explaining that deleting a message also deletes the file attached to it.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

It clearly says when to use this tool: recalling your own message, and indirectly deleting an old file in a group by deleting the message it is attached to. It also gives an exclusion rule: messages not sent by the bot fail, for Feishu policy reasons rather than permission reasons. It never names a specific sibling tool such as feishu_file_delete, so the agent must infer which alternative applies instead.

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