Skip to main content
Glama

get_qzone_public_replies

Read-only

Read paginated replies to a QQ Zone public feed comment by passing the original feed and comment objects, with cursor support to continue from the previous reply page.

Instructions

继续读取指定评论的回复 feed 必须原样取自 get_qzone_public_feeds 的 feeds 数组,不能用旧说说 tid 拼造;示例中的占位字段须整体替换。 comment 可取 get_qzone_public_feed_detail 返回的 feed.feed.cell_comment.comments,或后续评论页;保留完整对象。 首次续读使用评论自带的 reply_attach_info;之后传上一回复页的游标。 Returns: 上游回复页对象,保留回复、分页和未知字段。

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": {
      "feed": "<feed>",
      "comment": "<comment>"
    },
    "name": "get_qzone_public_replies"
  }
}

Input Schema

NameRequiredDescriptionDefault
feedYesget_qzone_public_feeds 返回的完整 feeds 条目,保留所有原始 cell 字段
cursorNo上一回复页的 reply_attach_info;省略则使用评论自带游标
commentYes详情或评论页返回的完整评论对象,保留 user 等原始字段
page_sizeNo请求的回复数量

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A4.1/5.0
Behavior4/5

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

The readOnlyHint/openWorldHint/destructiveHint annotations already declare the safety profile, so the description is not carrying that burden. It still adds behavior beyond the annotations: it preserves unknown fields on the upstream reply page, it makes cursor progression stateful across pages, and it warns against synthesizing identifiers. It says nothing about rate limits or what an empty or missing reply page looks like.

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?

It is dense but front-loaded: the action comes first, then the provenance constraints, then the cursor rule, then the return value. The note about replacing placeholder fields in an example assumes the agent can see that example, so it reads as slightly out of place, but overall there is little waste.

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 paginated tool with nested objects and no output schema, the definition covers the required inputs, the cursor lifecycle, and the return value. The only gaps are error or empty-page handling and the meaning of page_size, both of which are minor for a read-only continuation tool.

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%, so all four parameters are already documented, which sets the baseline at 3. The description does add provenance meaning for feed and comment, and it explains how the cursor changes between the first and later pages, but it does not cover page_size or the shape of the nested objects.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

The opening clause states a specific verb and resource: continue reading the replies of a designated comment. It also names the sibling tools that supply its inputs (get_qzone_public_feeds, get_qzone_public_feed_detail), which implicitly separates it from the top-level comment readers, though it never explicitly says which sibling to use for listing comments rather than replies.

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 a concrete call sequence: take feed verbatim from the get_qzone_public_feeds feeds array, take comment from feed_detail's feed.feed.cell_comment.comments or a later comment page, use the comment's own reply_attach_info for the first read, then pass the previous reply page's cursor. It also states a negative rule: do not fabricate a tid from an old post.

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

Deploy Server

Other Tools