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

Annotations only cover readOnly/openWorld; the description adds two things they do not: the call costs 1 credit and the result set is limited to the first screen of reviews rather than the complete set. It does not discuss rate limits or failure modes for invalid/expired product URLs, which keeps it short of a 5.

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?

Four short sentences, front-loaded with what is returned, then the scope limit, then the market default, then the cost. No filler and every sentence carries information the agent would otherwise have to guess.

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, describing the return fields (rating, reviewer, photos, variant) is the right move, and the region/cost notes cover the main call-shaping concerns. Pagination behavior is left to the cursor parameter description in the schema rather than being explained, a minor gap.

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 already 80%, so the baseline is 3; the description adds the region default of US, which the schema does not state. cache_max_age remains undocumented in both places, so it is not a full 5.

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 (fetching the reviews shown on a TikTok Shop product page) and enumerates returned fields (star rating, reviewer, photos, purchased variant). It is clearly distinguishable from tiktok_product / tiktok_shopProducts, which return product data rather than reviews.

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 scope caveat 'That is the page's first screen, not every review' tells the agent when this tool is insufficient, and the credit cost frames it as a paid call. It stops short of naming a sibling alternative for full review history or for product details.

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