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

Annotations already cover read-only and open-world safety, and the description adds valuable behavior beyond them: the feed is personalised even when logged out, non-reproducible between calls, and costs 1 credit. It doesn't describe the response shape or pagination, but for a simple feed that's a minor gap.

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 tight sentences: identity first, then the volatile/personalised caveat, then cost. Every sentence earns its place with zero filler.

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?

For a no-required-param feed with annotations and no output schema, the definition covers what the tool returns conceptually and its cost and volatility. The only real omission is meaning for cache_max_age, which is left undocumented in both schema and description.

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 67% – count and region are documented, cache_max_age is not. The description adds no parameter semantics at all, so the undocumented cache_max_age remains opaque, though the documented ones carry the usage. 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?

States a specific verb and resource ('TikTok's logged-out For You feed for a region') and makes the nature of the data unambiguous – a live anonymous feed, not a stable ranking. This clearly separates it from siblings like tiktok_popularVideos or tiktok_hashtagVideos.

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 clear context for when this is the right tool: when you want what the platform pushes to a brand-new visitor right now. It does not explicitly name alternatives (e.g. 'use tiktok_popularVideos for a curated stable ranking'), so the when-not guidance is implied rather than stated.

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