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

Annotations only declare readOnlyHint and openWorldHint, but the description adds several behavioral facts the agent could not otherwise know: the mp4 URL expires 2 hours after issuance (so it must be consumed promptly), resolution is capped at 720p, the call costs 1 credit, and specific fields (title, uploader, counts, upload date) are deliberately null so the agent won't report them as broken. This is exactly the context annotations cannot carry.

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?

Five short sentences, each carrying distinct information: payload, part selection, null fields, expiry, cost. The most decision-relevant facts (what you get, expiry, cost) are front-loaded and nothing is padded.

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, two-parameter tool with no output schema, the description covers the return contents, the expiry constraint, the resolution cap, and the credit cost, which is nearly everything an agent needs. The only remaining gap is the undocumented `cache_max_age` parameter and any note on failure modes for non-public videos.

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 50%: `url` is documented in the schema and the description adds real meaning on top by explaining that `?p=` in the URL selects a part of a multi-part video. The second parameter, `cache_max_age`, is unexplained in both the schema and the description, leaving half the surface undocumented.

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 states a concrete verb and resource and enumerates the exact payload: mp4 address (capped at 720p), description, tags, duration, first frame. It also scopes the tool to public Bilibili videos, which separates it from the many other *_video siblings (youtube_video, vimeo_video, rumble_video) that cover different platforms.

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 rather than stated: an agent can infer this is the tool for pulling a video file and metadata from a BV id or URL, and the `?p=` note tells it how to target a specific part of a multi-part video. However, there is no explicit when-to-use vs. when-not guidance, no pointing to a search/channel sibling for discovery, and no statement about failure cases such as private or region-locked videos.

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