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

The annotations declare readOnlyHint=false, openWorldHint=true and destructiveHint=false, which is mildly counterintuitive for a search; the description earns credit for explaining that gap by disclosing 'Saved in the user's Puley history', so the non-read-only flag is accounted for. It also discloses the ranking behavior ('most sold first'). It says nothing about how live the data is, result freshness, or what happens when a country has no shop coverage, so the disclosure is partial rather than rich.

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 description is two dense, front-loaded sentences with essentially no filler; the primary payload (what you get back and how it is ordered) comes first. The phrasing is telegraphic — 'limit: 5 to 30. Saved in the user's Puley history.' reads as stitched fragments — which slightly hurts scannability but wastes no words.

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 takes on the job of describing the result shape (price, sold count, rating, reviews, shop, link) and ordering, which is exactly the right allocation of effort. Annotations cover the safety profile and are consistent with the stated history side effect. The remaining gap is search-syntax guidance, which is the one thing an agent could get wrong on first call.

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 0%, so the description must carry parameter meaning, and it does for two of three: country gets concrete accepted values ('US, GB or another TikTok Shop country') and limit gets an explicit range ('5 to 30') that the bare schema does not express. The required `search` parameter is only implied by 'for a search' with no guidance on whether it takes a product name, keyword, or category, so the compensation is incomplete.

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 states a specific resource and question — products selling on TikTok Shop for a given search — and enumerates the returned fields (price, number sold, rating, reviews, shop, link) plus the sort order ('most sold first'). That is far more concrete than a tautology, and the name/title reinforce it. It stops short of 5 because it does not distinguish itself from near-neighbour siblings such as best_sellers, search_marketplace, or should_i_sell, which an agent could plausibly confuse with it.

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?

'for a search' plus the country list implies the discovery use case, and the suggestion that results land in Puley history hints at a browsing workflow. However, there is no explicit when-to-use clause, no when-not-to-use, and no named alternative tool for commercial-vs-organic product research. Usage is inferable but not directed.

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