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

No annotations are provided, so the description carries the full behavioral burden and falls short. It implies a read (returning metadata) but says nothing about auth/cookie requirements, rate limits, behavior on invalid BV ids or dead b23.tv links, or how multi-part videos are handled.

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?

A single front-loaded sentence that packs the verb, resource, output fields, and accepted identifier formats with no wasted words.

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?

With no output schema, listing the returned fields is a useful substitute and the accepted ID formats are covered. The gaps are behavioral (auth, errors) and the unexplained `page`/multi-part semantics, which is why it falls short of a 5.

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% and both params are documented in the schema, so the baseline is 3. The description adds nothing for the `page` (分P) parameter and only restates the accepted bvid formats that the schema already lists.

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 (Get) and resource (Bilibili video metadata) and even enumerates the returned fields (title, author, duration, stats, description). It does not explicitly contrast itself with the sibling tools (douyin/detail, xiaohongshu/note), though the 'Bilibili' scoping implies the platform split.

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?

Usage is only implied: use it when you need metadata for a Bilibili video. No when-not conditions, no mention of alternatives such as web/read for pages that aren't Bilibili videos, and no note that an invalid or private video will not resolve.

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

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

With no annotations, the description carries the full burden. It usefully discloses the returned payload, including the no-watermark play address and that galleries appear only for 图文 posts, and 'Get' implies a read operation. It says nothing about authentication, rate limits, or what happens for private/deleted/unavailable posts.

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 payload front-loaded and no filler; the second sentence efficiently covers accepted input forms. Every clause earns its place.

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 single-parameter read tool with no output schema, the description does the important work of listing what comes back, and there is no output schema that would otherwise cover returns. Minor gaps remain around auth/error behavior, but the agent has enough to call it correctly.

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% and the single target parameter is already documented in the schema (分享短链 / 视频链接 / 纯数字 ID). The description's 'share short link, video URL, or numeric id' is essentially an English restatement, adding no new syntax or format detail. Baseline 3 for a fully-documented schema.

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+resource ('Get a Douyin video/post') and enumerates the payload (caption, stats, author, play address, gallery), and the 'Douyin' qualifier naturally separates it from the platform-specific siblings bilibili/video and xiaohongshu/note. It never explicitly contrasts itself with those siblings, but the platform scoping makes selection unambiguous.

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?

Usage is implied by the identification of the resource type (Douyin posts and 图文 image posts), and the accepted input forms are spelled out. There is, however, no when-to-use/when-not guidance, no mention of auth or permission prerequisites, and no routing advice versus the sibling platform tools.

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

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

No annotations are provided, so the description carries the full behavioral burden. It usefully discloses that it runs through the user's logged-in Chrome session (an authentication/privacy-relevant fact) and that output is extracted main text rather than raw HTML, but says nothing about failure modes, rate limits, timeouts, or how long pages are handled.

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?

A single front-loaded sentence that states the action, the return format, and the session context with zero wasted words. Nothing could be trimmed without losing information.

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?

With no output schema, the description correctly covers the return value (main text as plain text) and the session context. However, for a no-annotation tool it is thin on behavioral completeness — no error/timeout behavior, no guidance on dynamic pages despite exposing a `wait` parameter, and no indication of output size limits.

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%, with each of the three parameters (url, wait, selector) already documented in the schema, so the baseline is 3. The description adds no syntax, units, or format detail beyond what the schema provides.

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 ("Read") and resource ("any web page"), plus the output shape ("main text as plain text"). The phrase "any web page" implicitly positions it as the generic reader against the site-specific siblings (bilibili/video, douyin/detail), but it never names or contrasts those siblings explicitly.

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?

There is no explicit when-to-use guidance, no prerequisites, and no mention of the sibling tools or when to prefer them over this generic reader. Usage is only implied by the verb "Read," leaving the agent to infer the routing decision itself.

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

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

No annotations are provided, so the description carries the full burden. It discloses that this is a read operation and what fields come back, but says nothing about authentication needs, rate limits, or failure behavior when the note is private or the token is missing.

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 action and return payload front-loaded, followed by the key invocation hint. No filler or redundancy.

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 single-parameter read tool with no output schema and no annotations, the description is nearly sufficient: it names the platform, the resource, and the return fields. The only meaningful gap is behavioral context (auth, failure modes) that an agent might want before invoking.

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 coverage is 100% and the single parameter's own description already covers both the full-URL-with-xsec_token preference and the 24-character ID alternative. The description merely restates the URL preference, adding no new syntax or format detail.

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?

The description gives a specific verb (Read) and resource (a Xiaohongshu note) and even enumerates the returned fields (title, author, text, engagement counts, tags). The platform specificity implicitly separates it from siblings like bilibili/video and douyin/detail, though it never names or contrasts them explicitly.

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?

"Pass a full note URL (with xsec_token) when possible" gives a parameter preference hint, which implies the tool is for fetching a note when you have a link. However, there is no when-to-use vs. when-not guidance and no routing toward web/read or other siblings.

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