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

Annotations already declare readOnlyHint and openWorldHint, so the safety profile is covered. The description adds genuinely non-annotated behavior: the cursor+search_id chaining contract for videos, the single-page limitation of users search, and a per-call credit cost. No contradiction with annotations.

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 compact sentences, front-loaded with the search modes and followed by the pagination caveat and cost. Every sentence carries operational information; nothing is redundant padding.

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 usefully names the response fields used for pagination (data.cursor, data.searchId) and the cost per call. It stops short of describing count/defaults or result shape, which is a minor gap for a 5-parameter search 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 only 40%, so the description must compensate, and it does for the pagination params: it clarifies that cursor and search_id are paired and only apply to videos, which is stronger than the schema's per-field notes. It is silent on count (bounds/default), leaving one parameter underserved.

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 and resource ('Search TikTok creators ... or videos by keyword') and disambiguates the two modes via the search_type enum values. It is clear about what the tool does, though it never contrasts itself with nearby siblings such as tiktokUser or tiktokVideo.

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?

Gives concrete usage rules: videos paginate from page 2 onward with the previous response's cursor/search_id, users search is single-page and ignores cursor, and each call costs 1 credit. No exclusions relative to sibling tools, but the in-tool mode/pagination conditions are explicit.

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