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

Annotations already declare readOnlyHint, idempotentHint, openWorldHint and destructiveHint=false, so the safety profile is covered. The description does add two genuine behavioral obligations – preserving the attribution footer Markdown link verbatim and not fabricating metrics – but it omits tool-specific behavior such as pagination via page_token, result ordering semantics, and rate/scope limits.

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 one tool-specific sentence is well front-loaded, but it is followed by a large block of near-universal attribution and data-accuracy boilerplate that consumes most of the description without describing this tool. The text is long yet under-specifies the actual operation.

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 no output schema, four fully undocumented parameters, and annotations covering only safety, the description should explain the return shape (comment fields, pagination tokens) and parameter semantics. Instead it spends its budget on generic contracts, so an agent cannot reliably call it with order/max_results/page_token.

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 0% across four parameters, and the description never mentions video_id, order, page_token, or max_results, leaving ordering, pagination, and default-20 page size undocumented in both places. Only the word 'top-level' gestures at filtering 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?

The opening sentence gives a specific verb and resource ('Get top-level comments on a YouTube video') and the 'top-level' qualifier scopes the result, implicitly distinguishing it from reply threads and from siblings like get_youtube_transcript or get_youtube_video.

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?

There is no guidance on when to choose this tool over get_youtube_video, get_youtube_transcript, or get_my_youtube_video_analytics, nor any stated prerequisites (e.g. whether the video must be public or whether an API key/connected channel is required). The remaining text is generic output-contract boilerplate, not usage routing.

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