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

Annotations already declare readOnlyHint=true, openWorldHint=true, destructiveHint=false, so the safety profile is covered. The description adds real operational context beyond that: no automatic retries and no automatic page iteration, plus an instruction to preserve provider fields and metric units. It still says nothing about result shape, rate limits, or provider error behavior for an open-world tool.

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?

Three short sentences, front-loaded, with no filler prose. The only inefficiency is the opening sentence, which spends a slot restating the tool name instead of carrying new 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?

With 15 parameters, no output schema, and an open-world provider, the description should at least indicate what comes back (a paginated list of livestream records with GMV/sold/audience metrics) and that page/pageSize must be driven manually. It conveys the no-auto-pagination constraint but leaves the return contract entirely to inference.

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 enum, min/max, and pattern constraints, so the baseline is 3. The only parameter-relevant addition is 'retain the provider metric definition without unit conversion,' which usefully clarifies that minGmv/maxGmv/minSold/maxAudience values are in provider-native units — but that same phrasing is already echoed in the schema descriptions.

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 first sentence 'TikTok Live Search' merely restates the tool name and title rather than describing the operation in a verb+resource form (e.g., 'search TikTok livestreams by keyword, category, and GMV/audience ranges'). It gives no signal distinguishing it from close siblings such as nexscope_chuhaijiang_tiktok_live_detail, nexscope_chuhaijiang_tiktok_live_related_products, or nexscope_tiktok_livestream_analytics.

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 description provides no when-to-use guidance and no named alternatives, despite dozens of adjacent TikTok livestream/analytics siblings. 'Execute only this operation' is an execution constraint, not routing guidance; an agent still cannot tell from this text when to pick live_search over live_detail or livestream_analytics.

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