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

Goes well beyond readOnlyHint/openWorldHint by disclosing page size (~20), the pagination round-trip ('Pass pagination.cursor back as cursor'), the presence of replyCursors per item, ranking churn behavior of `top`, and a cost of 1 credit. That is exactly the runtime context annotations can't express.

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?

Five short sentences, zero filler, and the identifying statement is front-loaded before pagination, reply routing, ordering, and cost. Every sentence carries distinct 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?

Pagination, reply traversal, and credit cost make this complete for a list tool with no output schema. The only shortfall is `cache_max_age`, which an agent cannot reason about from either the schema or the description.

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 50%, and the description compensates well for the two undocumented ones: it explains `order` semantics (top is re-ranked vs newest for polling) and how `cursor` flows from `pagination.cursor`. `cache_max_age` is left entirely unexplained in both schema and description, which is the remaining gap.

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 the resource and scope precisely — 'Top-level comments on a video, about 20 per page' — which immediately separates it from reply-fetching siblings like youtube_commentReplies. An agent knows what it retrieves without opening the schema.

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?

Routes to the alternative explicitly ('feed that cursor to /v1/youtube/video/comment-replies') and gives situational guidance for parameters ('Use order=newest when polling for new comments, since top is re-ranked'). Both the when and the alternative are stated, not inferred.

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