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

Annotations already cover read-only and open-world access, so the bar is lower. The description still adds two useful facts not in the annotations: the transcript is derived from existing captions (not speech-to-text) and the call costs 1 credit. It omits failure behavior when captions are absent and whether the returned text includes timestamps or segments.

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 plus a parenthetical cost note; nothing is wasted and the key qualifier ('from its captions') comes early. There is room for one more clause about the caption dependency without hurting readability.

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?

The tool is simple (1 required param, no nesting, no output schema), and the description covers what it fetches and its cost. However, with no output schema the description should say roughly what comes back (plain text vs. timed segments) and what happens when no captions exist — both are real gaps for a scrape-style tool.

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%, so the schema already documents both `url` and `language`, including the 'e.g. en' example. The description adds no meaning beyond the schema — no detail on whether `language` affects the transcript source or what happens if the requested language is unavailable. 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?

Names a specific resource (spoken-word transcript) and source (a TikTok video's captions), which lets an agent tell it apart from tiktok_video or tiktok_comments without opening the schema. It is a noun phrase rather than a verb phrase, but the intent is 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?

No statement of when to choose this over tiktok_video (video metadata) or the Instagram/YouTube transcript siblings, and no guidance on what to do when a video has no captions. The only implied usage cue is 'from its captions', which the agent must interpret itself.

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