Skip to main content
Glama

SocialDataX B站 Bilibili MCP

bilibili_get_content_comment_replies_by_comment_id

Read-only

根据内容评论目标和一级评论 ID 获取评论回复;用户已提供完整合法的 ID 组合时直接使用;已有内容 ID 或链接但缺少必需 ID 时,调用对应一级评论工具补全;缺少内容定位信息时向用户索取;不要传评论回复项的 comment_id。

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
comment_idYesB 站一级评论 ID;用户已提供时直接使用,否则可从一级评论结果 items[].comment_id 复制;不要自行构造,不要传评论回复项的 comment_id。
page_tokenNoBilibili 评论回复分页令牌。首次请求留空。继续翻页时必须将上一页返回的完整 next_page_token 原样作为 page_token 传回;page_token 是不透明分页令牌;不得修改、截断、缩写、脱敏、掩码、省略、规范化、重组或自行生成,不得用省略号替换中间内容。只能用于同一内容下同一条一级评论的回复分页链路,也就是同一 comment_object_id、comment_object_type 和一级 comment_id;不能跨能力、内容或评论复用。
comment_object_idYes被评论对象 ID;用户已提供时直接使用,否则从一级评论结果复制 comment_object_id;必须与同一条一级评论的 comment_id 和 comment_object_type 一起使用;不要自行构造。
comment_object_typeYes被评论对象类型编号;用户已提供时直接使用,否则从一级评论结果复制 comment_object_type;必须与同一条一级评论的 comment_id 和 comment_object_id 一起使用;不要自行构造。

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault
itemsYes当前页内容评论回复列表。
pointsYes本次成功调用的积分消耗与调用完成时的账户积分余额。
next_page_tokenYes下一页不透明分页令牌;为空表示没有更多评论回复。继续获取评论回复下一页时,必须将返回的完整 next_page_token 原样作为 page_token 传回;只能用于同一内容下同一条一级评论的回复分页链路,也就是同一 comment_object_id、comment_object_type 和一级 comment_id。不得修改、截断、缩写、脱敏、掩码、省略、规范化、重组或自行生成,不得用省略号替换中间内容;不能跨能力、内容或评论复用。

TDQS

A4.4/5.0
Behavior4/5

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

Annotations declare readOnlyHint=true and openWorldHint=true, so the description needn't restate those. It adds valuable behavioral context: the pagination semantics documented, though largely in the schema's page_token description, is reinforced in the tool description. The instruction not to construct IDs from scratch and to use values from the top-level comment result adds behavioral context beyond annotations.

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 description is a single, dense sentence that front-loads the primary purpose and then provides concise routing guidance. Every clause earns its place; 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?

The tool has a clear output schema (next_page_token documented), 100% schema coverage, and annotations for safety. The description covers the main usage decisions. The only minor gap is that it doesn't explicitly mention the relationship to the sibling reply-fetching tools beyond the top-level comment tools, but given the output schema and annotations, this is adequately complete.

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 each parameter already has detailed descriptions in the schema (copy from top-level comment results, do not construct, must be used together). The tool description adds the explicit instruction about not passing a reply item's comment_id, which complements the schema, but the description itself adds only marginal value over the already-rich schema.

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 clearly states the verb (获取/retrieve), resource (评论回复/replies to a top-level comment), and target (by content comment target and top-level comment ID). It distinguishes from the sibling tools bilibili_get_content_comments_by_id and bilibili_get_content_comments_by_url, which fetch top-level comments, whereas this one fetches replies to a specific comment.

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?

Explicitly provides usage guidance: use directly when a complete legal ID combination is given; call the corresponding top-level comment tool to complete missing IDs; ask the user when content location info is missing. Also states a clear exclusion — do not pass the comment_id of a reply item. This exceeds typical guidance.

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

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.

TDQS

A3.9/5.0
Disambiguation5/5

Each tool targets a distinct resource and input mode, and the by_id/by_url variants are clearly separated by input type. The descriptions explicitly warn against passing the wrong ID types (e.g., comment_id vs post_id), making misselection unlikely.

Naming Consistency4/5

The vast majority follow a consistent bilibili_<verb>_<object>_by_<identifier> pattern, with get/search/submit as clear verbs. The one account-level tool (socialdatax_get_points_balance) breaks the bilibili prefix but is a minor deviation.

Tool Count4/5

22 tools is slightly above the ideal 3-15 range, but the count is justified by the broad Bilibili data surface: content, comments, user content, search, download, transcription, and account balance. Many tools are paired id/url variants of the same logical operation, which inflates the count without adding conceptual clutter.

Completeness4/5

The set covers the core Bilibili content lifecycle well: details, comments/replies, likes/reposts, user posted content, search, video download, speech-to-text submission/status, and points balance. Minor gaps exist (e.g., no user social graph or dynamic/user search), but they are workarounds rather than dead ends.

Resources