Get trending NudiTok videos by engagement for a time window (max 20).
| Name | Required | Description | Default |
|---|---|---|---|
| page | No | Page number (1-based) | |
| cursor | No | Opaque pagination cursor from a prior call | |
| window | No | Time window | |
| per_page | No |
| Name | Required | Description | Default |
|---|---|---|---|
| count | No | ||
| videos | No | ||
| has_more | No | ||
| next_cursor | No |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description must carry the behavioral burden. It conveys a read-only intent, the trending-by-engagement ordering idea, and a limit of 20, but it does not explain page/cursor interplay, direction of engagement ordering, or default behavior. This is minimal but not wholly uninformative.
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 sentence with no filler; the core resource, selection criterion, and limit are all stated directly. The most important decision-facing 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?
The output schema covers return shape and most parameters are documented, so basic invocation is possible. However, the description omits practical context such as how pagination parameters interact, what happens when no params are provided, and when to prefer a sibling tool, leaving the agent to infer.
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?
The schema already documents page, cursor, and window, and the description adds only the 'max 20' cap tied to per_page. At 75% schema coverage, the description does not need to compensate heavily, and it provides marginal additional meaning.
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 specific verb and resource, 'Get trending NudiTok videos by engagement', and adds a time-window constraint and a cap of 20. This clearly separates it from siblings like get_feed, get_user, and search_content.
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 guidance is provided about when to use this tool versus the six sibling tools. An agent must infer that 'trending by engagement' is the selection criterion, but no when-to-use or when-not-to-use context is stated.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Add one secure layer between your agents and this server.
Each tool targets a distinct data type or access pattern: feed, trending, user, video, creators, tags, and search. The only mild overlap is between get_feed and get_trending, but their descriptions clearly separate 'newest' from 'trending by engagement.'
Tool names mostly follow a consistent verb_noun pattern with get_ for single/current items and list_ for directory-style browsing. get_feed and get_trending use get_ for collection-style endpoints, which is a slight deviation from the otherwise clear list_ convention for collections.
Seven tools is a well-scoped size for a read-only content browsing API. Each tool covers a meaningful content surface without redundancy or bloat.
The surface covers the core browsing workflows: discovering videos via feed/trending/search, inspecting users, videos, creators, and tags. Minor gaps exist such as no per-tag detail endpoint and no comment access, but these are acceptable for a public read-only client.
