dynamic_feedRead followed Bilibili dynamics feed with authors, text, images, video cards, and interaction counts. Paginate using page or the returned next_offset cursor, with 20 items per page.
读取关注动态流，包含作者、文本、图片、视频卡片与互动数。支持翻页：用返回的 next_offset 作为 offset 继续，或直接传 page；B 站每页 20 条。
| Name | Required | Description | Default |
|---|---|---|---|
| page | No | 页码，从 1 开始；不传 offset 时生效 | |
| type | No | 动态流类型 | all |
| offset | No | 游标；优先于 page。把上一页返回的 next_offset 传进来 |
Changes observed during successful MCP inspections.
v0.1.0-beta.2Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations only declare readOnlyHint and openWorldHint, so the description carries the burden of return-shape disclosure and does so: it names the fields returned (author, text, media cards, interaction counts) and states the 20-items-per-page cadence. It stops short of describing error or rate-limit behavior.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Two tight sentences with the purpose front-loaded and pagination mechanics following; nearly every clause earns its place. Slightly dense packing of cursor semantics at the end.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a read-only feed tool with annotations covering the safety profile and no output schema, the description supplies the return contents and pagination model an agent needs. It omits any statement that this is the authenticated user's following feed, which an agent would otherwise have to infer.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 100%, so the schema already documents page, type, and offset, including offset's precedence over page. The description restates that offset precedence and adds only the page-size fact (20 per page), so baseline 3 is appropriate.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
States a specific verb (读取) and resource (关注动态流) and enumerates what the feed contains (author, text, images, video cards, interaction counts), which clearly separates it from sibling post_dynamic. It does not explicitly name an alternative tool, so it falls just short of full sibling differentiation.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description explains how to paginate (reuse next_offset, or pass page) but never says when this tool should be chosen over notifications, search, or user_videos. Usage is implied by the resource name rather than stated as a when/when-not rule.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.