Skip to main content
Glama

把多条消息合并成一份记录转发

feishu_merge_forward

Combine 2–50 Feishu messages into a sourced conversation-record card and send it to a chat or user, making it easy to share a whole discussion instead of forwarding messages one by one.

Instructions

把 2~50 条消息打包成一张「会话记录」卡片发到别处,适合「把这段讨论转给另一个人看」。和 feishu_forward 的区别:forward 是一条一条转,merge_forward 是合成一份带来源的摘要。

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_ids": "<message_ids>",
      "receive_id": "<receive_id>"
    },
    "name": "feishu_merge_forward"
  }
}

Input Schema

NameRequiredDescriptionDefault
receive_idYes发到哪里:chat_id(oc_ 开头)或 open_id(ou_ 开头)。
message_idsYes要合并的消息 id 列表(om_ 开头),2~50 条。
receive_id_typeNoreceive_id 的类型,默认 chat_id。

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.1

TDQS

A4.2/5.0
Behavior3/5

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

The annotations already declare readOnlyHint=false and openWorldHint=true, so the agent knows this tool writes data and can send it outside the current conversation context. The description adds that the output is a card with source attribution and that the input is capped at 2-50 messages. However, it does not describe permissions required, whether the original messages are altered, or what the recipient sees beyond 'a summary with source.'

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, no filler: the capability and the scope come first, and the sibling comparison comes second. Every clause carries information the agent needs.

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 3-parameter send tool with no output schema, the description is nearly complete: it covers what gets built, the size bound, and the sibling distinction. It leaves out only side-effect details (recipient notification behavior, permission needs) that the annotations partially cover via openWorldHint.

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 description coverage is 100%, so all three parameters (receive_id, message_ids, receive_id_type) are already documented with the oc_/ou_ prefixes, the om_ ids, and the 2-50 limits. The description repeats the 2-50 bound and the 'summary with source' framing but adds no syntax or format meaning beyond the schema. 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?

The description names a concrete action (打包成「会话记录」卡片发到别处) with an explicit scope (2~50 条消息) and then contrasts it with the sibling feishu_forward by explaining that forward sends messages one by one, while this tool merges them into one summarizing record that includes the source. An agent can distinguish this tool from feishu_forward without opening either 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?

The description gives an explicit usage scenario (把这段讨论转给另一个人看) and names the alternative feishu_forward along with the condition that selects it: forward one message at a time, or merge them into one summary. The routing decision is fully specified.

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