Check how TikTok will treat a video before posting it

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

Goes well beyond the annotations: it names the 768 KB read cap, states that nothing is published or changed, discloses a rate limit of 60 checks per hour per account, and explains what each verdict means (including the specific triggers for 'recompressed': HEVC/AV1, HDR or 10-bit, above 1080x1920, above 30 fps, above 16 Mbps). These are exactly the operational constraints an agent needs before calling.

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?

The core purpose and verdict taxonomy are front-loaded, and the safety/rate-limit facts are packed into the tail. It is a single dense paragraph with a long parenthetical list, which is efficient but slightly run-on; splitting the verdict definitions would improve scannability without adding length.

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?

There is no output schema, but the description compensates by naming the returned fields (verdict, advice, message_for_user, plus codec/size/fps/bitrate details) and explaining what each contains. Combined with one fully-documented parameter and complete annotations, an agent has everything needed to call it correctly and interpret the result.

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 already specifies https, .mp4/.mov, and length bounds, so the schema carries most of the burden. The description still adds value by clarifying that a share page will not work and that an upload's media_url is a valid source, and by explaining the 'unknown' outcome when the header cannot be read.

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 opens with a concrete verb and resource (reads a video file's header, reports what TikTok will do with it) and enumerates exactly what it returns: codec/profile, dimensions, fps, bitrate, duration, HDR, audio codec, verdict. It is unmistakably distinct from the sibling posting/scheduling tools because it explicitly operates before posting and publishes nothing.

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 'before posting it' framing plus 'an upload's media_url works' tells the agent this is a pre-flight diagnostic that pairs with an existing upload, and the verdict vocabulary (keeps_quality / recompressed / unknown) makes the use case concrete. It stops short of explicitly naming which sibling tool to call instead for posting or fetching the media_url, so it does not fully close the loop on alternatives.

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