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

Annotations already mark this as read-only and non-destructive, and the description adds substantial behavior beyond that: credit costs per successful entry, the distinction between auto generation and captions-only retrieval, duplicate handling, input-order preservation, and per-item results. These are exactly the kind of operational traits an agent needs to predict cost and behavior 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?

Three tightly packed sentences, each adding distinct value: what the tool fetches and returns, cost and mode behavior, and duplicate handling. There is no filler or repetition of schema details, and the most important batching information is front-loaded.

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?

Given the output schema exists and annotations cover the read-only safety profile, the description sufficiently covers invocation-critical context: input limits, per-item results, credit costs per successful entry, mode semantics, and duplicate behavior. The only minor omission is explicit naming of the singular or captions-only sibling tools, but that does not make the definition incomplete for selecting and calling this 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 description coverage is 0%, so the description carries the full burden for parameter meaning. It does so effectively: 'urls' is clarified through the 1–10 count, input order, and duplicate handling, and 'mode' is clarified through the auto/captions distinction, cost difference, and generation behavior. This goes well beyond the raw enum and array 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?

The description uses a specific verb ('Fetch') and resource ('transcripts for 1–10 TikTok URLs'), immediately communicating both the action and the batching scope. It distinguishes itself from the singular sibling get_tiktok_video_transcript by explicitly stating the 1–10 URL batch behavior and per-item result structure.

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 makes the primary use case clear: fetching transcripts for multiple TikTok URLs at once. It also explains the two mode options and their behavioral trade-offs, which helps an agent choose between them. It does not explicitly name the singular tool or captions-only sibling as alternatives, but the batch context is strong enough to imply when this tool is appropriate.

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