Skip to main content
Glama

删云空间里的文件(不是群消息附件)

feishu_file_delete
Destructive

Deletes files, docs, sheets, bitables, or empty folders in Feishu My/Shared Space using a cloud file token from drive listings.

Instructions

删除云空间(我的空间/共享空间)里的文件、文档、表格、多维表格或空文件夹。注意:群聊里发的文件是消息附件,那个用 feishu_recall 删消息;这里的 file_token 是云文档体系里的 token(来自 feishu_drive_list),两者不通用。

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": {
      "file_token": "<file_token>"
    },
    "name": "feishu_file_delete"
  }
}

Input Schema

NameRequiredDescriptionDefault
typeNo文件类型,默认 file。文件夹要删必须先清空。
file_tokenYes云空间文件的 token(来自 feishu_drive_list)。

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.1

TDQS

A4.4/5.0
Behavior3/5

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

Annotations already declare destructiveHint=true, readOnlyHint=false, and openWorldHint=true, so the core safety signal is covered. The description adds the token-domain warning and the empty-folder prerequisite, but says nothing about whether deletion is permanent or recoverable, whether items go to trash, or what permissions are required — gaps that matter for an irreversible write.

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?

Two sentences, front-loaded with the action and scope, followed by a bolded caveat that occupies exactly as much space as its importance warrants. No filler and no restatement of the tool name.

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 destructive tool with a fully described schema and no output schema, this covers purpose, scope, and the main sibling confusion. The only real omission is post-deletion behavior (trash vs. permanent, recoverability), which is the one thing an agent cannot get from the structured fields.

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 both parameters are already documented, including the enum values and the empty-folder rule. The description still earns credit beyond the schema by specifying the provenance and non-interchangeability of file_token, which prevents a realistic misuse.

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 specific verb (delete) plus the exact resource class — files, docs, sheets, bitables, or empty folders in 我的空间/共享空间 — and explicitly excludes chat message attachments. An agent can distinguish it from feishu_recall and feishu_drive_list without opening any 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?

Names the failure mode directly: chat-posted files are message attachments and must be removed with feishu_recall instead. It also states where file_token comes from (feishu_drive_list) and that the two token systems are not interchangeable, which is exactly the routing information an agent needs before calling.

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