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

The description discloses the underlying data source (FastMoss) and that results span global TikTok e-commerce markets, which adds context beyond the annotations. With readOnlyHint=false and openWorldHint=true already present, it still says nothing about quota/credits, response latency, or result volume for a 15-parameter query; note the mild tension between 'search' and readOnlyHint=false, though it does not rise to a contradiction.

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 opening sentence is well-formed and front-loaded, but the trigger list is padded with literal duplicates ('TikTok product search' twice, 'TikTok creator sales' twice, 'TikTok commission rate' twice, 'TikTok GMV analysis' twice), wasting space that could have described behavior or sibling routing.

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?

Data source, filter dimensions and sorting are covered, and the schema fully documents all 15 parameters; with no output schema the description should still say roughly what a result row contains and note the pageSize cap of 10, which it omits. Adequate to invoke, thin on what comes back.

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 100% with per-field descriptions, enum-like region and orderField lists, and nested range-object formats, so the schema carries the parameter burden. The description's 'multi-dimensional filtering (category, shop type, commission rate, sales, creator count, etc.) and sorting' merely echoes parameter names without adding format or interaction rules, so baseline 3 applies.

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 and filter TikTok global e-commerce products') plus the data provenance ('based on FastMoss data'), which is more than the title restated. However, it never distinguishes itself from the many adjacent TikTok product-search siblings (nexscope_tiktok_product_search, nexscope_data_fm_product_search, nexscope_chuhaijiang_tiktok_product_search), so an agent cannot tell which search tool to pick.

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 'Trigger when users mention...' list gives clear, concrete intake conditions (product selection, commission rate, bestseller tracking, GMV analysis) and explicitly says to fire even when FastMoss is not named, which lowers false negatives. It offers no when-not conditions and no routing to alternative TikTok product tools, so it stops short of full selection guidance.

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