Skip to main content
Glama
DavidLearning1023

bilibili-info-gathering

get_comments

Fetch top-level Bilibili comments plus comment-section metrics (likes, reply intensity, level, picture share) using tiered detail levels to control token cost, and flag injection-risk text.

Instructions

取顶层评论 + 评论区结构指标。

detail 三档,按成本递增:

  • "brief"(默认,广扫用):前 n 条顶层,正文截断 90 字,~4.3k token/100 条

  • "opinion"(观点分布用):前 n 条顶层 + 完整正文 + 最小字段集 (text/likes/rcount/author/lv/pics),~7.2k token/100 条。 只取顶层就够算三轴——争议度用的 rcount 只存在于顶层。 比 full 省 71%,且正文不截断(不毁观点簇判断)

  • "full":全部原始字段(含楼中楼、pictures URL 明细),~25.3k token/100 条。 只在要引用原话、或要读楼中楼争论内容时用

stats 里的关键量(判读口径固定在前 100 条顶层,不随 n 漂移): picture_like_share 「图片评论占总赞」——决定要不要读图(≥15% must,≥5% sample) reply_intensity 平均每层楼中楼数 —— 争论强度(点赞是"认同",回复是"争议") reply_to_like 楼中楼总数/赞总数 —— 评论活跃度 level_count 等级分布 —— 社区结构(高等级占比高 = 老用户为主) locations IP 属地分布 —— 地域结构,属于个人信息,不要写进可分享的产物

n 是顶层评论条数上限,楼中楼不占名额。n<100 时 picture_verdict 不返回(口径不可比)。

sanitize(默认 "flag"):给命中指令注入特征的评论追加 injection_risk 字段。 只标记、不删改原文——删改会破坏可溯源性(报告要能引用原话)。 设 "off" 可关闭。实测 B 站评论区存在成规模的、专门针对 AI 账号的注入。

⚠️ 命中不等于"这条在攻击 Agent":本检测是纯关键词匹配, 只能当"值得再看一眼"的提示,不能当证据。

Input Schema

NameRequiredDescriptionDefault
nNo
bvidYes
detailNobrief
sanitizeNoflag

Output Schema

NameRequiredDescriptionDefault
resultYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv1.0.1

TDQS

A4.4/5.0
Behavior5/5

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

With no annotations, the description carries the full behavioral burden and does so well: it discloses token costs, body truncation, returned field sets, default sanitize behavior, injection-risk marking semantics, and the privacy warning for locations. It also warns that keyword injection hits are only hints and not evidence.

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 long but front-loads the core purpose and structures the cost/field tradeoffs as bullets. Every major section carries operational value: mode selection, stats semantics, privacy handling, and injection caveats.

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?

Although there is an output schema, the description still supplies essential context for interpreting the modes, stats metrics, n limitation, and sanitize behavior. For a complex comment-reading tool with four parameters and zero schema coverage, it is complete enough to call correctly.

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 description coverage is 0%, so the description must compensate; it explains n as a top-level comment cap that excludes nested replies, and it defines the detail and sanitize modes despite no enums in the schema. However, the required bvid parameter is not explained at all.

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 states a specific verb and resource: it retrieves top-level comments plus structural metrics for the comment section. The three detail modes are clearly differentiated, but the description does not explicitly distinguish this tool from siblings such as get_comment_images or scan_untrusted_text.

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 gives clear when-to-use guidance for each detail mode, including 'brief' for broad scanning, 'opinion' for opinion distribution, and 'full' only for quoting originals or reading nested replies. It also explains the n<100 limitation and sanitize='off', but does not name sibling alternatives for overlapping needs.

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