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

Annotations only supply openWorldHint=true and a readOnlyHint=false, so the description adds real value by inventorying returned measures (views, likes, comments, shares, revenue, GPM, ad metrics) and the filter dimensions. It discloses nothing about cost, auth, rate limits, or pagination behavior, and it describes only lookup semantics while the annotation declines readOnlyHint — a mild tension an agent must resolve on its own.

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 sentence is well front-loaded with both capabilities, but the trigger enumeration is repetitive and the final sentence largely restates the trigger list. Roughly a third of the text is keyword bait rather than operational 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?

Absent an output schema, the description does name the returned metrics, which covers the biggest gap. But for a 15-parameter, two-mode tool with a nested sortField and no required parameters, it omits how the modes interact, which filters apply to which mode, and how sortField is shaped — leaving the agent to infer routing from the schema alone.

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%, so baseline 3 applies. The description maps region/currency/language/dateRange to leaderboard filtering and explains that videoId retrieves the detail metrics, which is genuinely additive. It never explains the mode switch (videoId present vs absent) or the roles of shop_id, creator_id, product_id, category_id, revenue_range, followers_range, ads_roas, and the undocumented nested sortField object.

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 concrete verbs and resources: search TikTok e-commerce trending promotional video leaderboards via Kalodata, and query detail metrics for a specific video via videoId. That is far more specific than the name alone. It fails at the sibling-differentiation half of a 5, since near-identical siblings (nexscope_tiktok_video_rank, nexscope_tiktok_video_search, nexscope_data_kd_video_rank, nexscope_data_kd_video_detail) are never named or contrasted.

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 TikTok video search / ranking / detail' list gives implied usage conditions, and the closing sentence says to fire even without the word 'kalodata'. However, no when-not and no alternatives are given, and the broad 'TikTok video search' trigger overlaps directly with the dedicated nexscope_tiktok_video_search sibling, leaving the agent no basis to choose between them.

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