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

The description discloses the upstream data source (Kalodata) and the metric set returned per store (revenue, sales volume, channel revenue breakdown, creator count), which is genuinely useful since there is no output schema. However it says nothing about rate limits, quota, data freshness, region coverage limits, or the errcode 501 pagination boundary. There is also mild tension with the annotations, which do not declare readOnlyHint=true even though the described operations are pure reads.

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 first two sentences are well structured and front-load the capability, but the remainder is a bloated trigger-keyword dump that repeats 'TikTok shop leaderboard', 'TikTok top shops' and 'TikTok store ranking' two to three times each. That spam dilutes the signal and inflates the description without adding any callable 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?

Return-value coverage is adequate given no output schema, but for a 12-parameter tool with a nested sortField object and zero required parameters, the description omits any defaults, mode-selection rules, pagination constraints, and how the mutually exclusive filter parameters (region/currency/language/dateRange/category/revenue_range) combine. Enough to attempt a call, not enough to call it confidently.

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%, so every one of the 12 parameters is already documented, including the shopId provenance note and pagination ranges. The description adds only the mode-switch insight (shopId → detail), which the schema already conveys; it says nothing extra about sortField's empty-object convention, revenue_range syntax, or category_ids behavior.

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 pair: search TikTok Shop store leaderboards via Kalodata and fetch per-store detail metrics when a shopId is supplied. The dual-mode nature is discernible from the text, but the tool is not differentiated from near-duplicate siblings (nexscope_data_kd_shop_rank, nexscope_data_kd_shop_detail, nexscope_chuhaijiang_tiktok_shop_detail, nexscope_tiktok_seller_detail), so an agent still cannot tell which one is canonical.

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?

Usage is only implied: the presence of shopId switches the call from leaderboard listing to store detail. The long trigger-phrase list is keyword bait rather than decision guidance — it never says when to pick this tool over the similarly named shop-rank or shop-detail siblings, nor which parameters are required per mode.

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