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

Annotations already cover read-only and open-world nature, and the description adds genuinely non-obvious behavior: per-call pricing ($0.02), x402/USDC payment passed in _meta, which failure cases are not billed, and pagination semantics. It stops short of describing rate limits or latency, and the 'idempotentHint: false' implication for cursor reuse is left implicit.

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 resource and scope are front-loaded, and the semicolon-separated clauses each carry distinct information (return fields, pagination, billing). It is dense but slightly overpacked, mixing retrieval behavior and payment mechanics in a single run-on sentence.

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 enumerates the returned fields (caption, plays, likes, comments, shares, language, cover, time, URL, creator name, verification, followers) and the pagination model, plus payment requirements. Only minor gaps remain, such as what happens when the cursor is stale or the exact shape of the next_cursor response.

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% with both parameters described, so baseline is 3. The description's 'by handle or tiktok.com/@ URL' mostly restates the handle schema text, and it adds no format detail for cursor beyond the schema's 'next_cursor of the previous page.'

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 ('latest public videos of one TikTok account') and the accepted identifier forms, which cleanly separates it from siblings like tiktok_search, tiktok_followers and tiktok_following. An agent can pick this tool without opening the schema.

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?

It implies usage via 'by handle or tiktok.com/@ URL' and explains that next_cursor pages back, but never names an alternative or states when this is preferred over tiktok_search. The billing rules ('bad input is free; not found or no match is not charged') hint at retry decisions but are not framed as guidance.

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