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

Annotations already declare readOnlyHint=true, destructiveHint=false and openWorldHint=true, so the safety profile is covered and the bar is lower. The description adds genuine context by naming FastMoss as the data source and the global (multi-region) scope. It says nothing about pagination caps, result size, or what kind of payload comes back, which for a 15-param search tool is a missed opportunity but not a violation.

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 purpose is front-loaded well, but the trigger block is padded with verbatim duplicates ('TikTok product search', 'TikTok creator sales', 'TikTok commission rate', 'TikTok GMV analysis' each appear twice) plus a redundant framing sentence. Roughly half the text could be deleted without losing information.

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?

No output schema exists, so the description should convey what comes back; it does not describe the result structure or pagination behavior at all. It does cover data provenance and the filter dimensions, which is enough for an agent to call the tool, but not enough to interpret or iterate on results.

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 100%, including units for commissionRateRange and enum options for region/orderField, so the schema carries the parameter burden. The description only restates the filter families already documented in the schema and adds no extra semantics (no defaults, no interaction between filters, no guidance that pageSize caps at 10).

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 opening sentence gives a concrete verb and resource: search/filter TikTok global e-commerce products from FastMoss data, with named dimensions (keyword, category, shop type, commission, sales, creator count) and sorting. However, it never distinguishes itself from the many near-identical TikTok siblings, in particular nexscope_tiktok_product_search and nexscope_tiktok_product_analytics, which an agent could easily pick instead.

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 list only says 'use this when the user mentions TikTok product data/analysis', a scope so broad it overlaps nexscope_tiktok_product_search, nexscope_tiktok_product_analytics and nexscope_tiktok_top_selling_products. There is no when-not condition, no named alternative, and no prerequisite or data-scope constraint (e.g. FastMoss coverage limits) that would let an agent route between them.

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