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

Annotations only declare readOnlyHint and openWorldHint; the description layers on the genuinely useful behavioral facts — ~20 item cap, empty-list-not-error semantics when comments are disabled, no reply threads, no pagination — plus a concrete pricing model ($0.002 USDC via x402 on Base/Solana/Arc) and the fact that failed calls are not charged. That billing detail is critical for an agent deciding whether to retry.

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?

Four tight sentences: scope and payload first, then edge-case behavior, then exclusions, then cost. No filler, and the most decision-relevant facts lead.

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 an output schema present the return shape need not be restated, and the description still covers the things structured fields can't express: pagination limits, empty-result semantics, and per-call cost/charging rules. Nothing an agent needs in order to call this correctly is missing.

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?

Single parameter with 100% schema coverage, so the schema already documents videoId and its 11-character format. The description adds only the 'one YouTube video' scoping, not extra syntax or validation guidance; the enumerated field list describes the response, not the input. Baseline 3 is appropriate.

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 and resource ('first page of top comments... on one YouTube video') and enumerates exactly which fields come back (author, verified/creator flags, text, like/reply counts, age). The platform is explicit, which cleanly separates it from the sibling comment tools (social_bilibili_comments, social_tiktok_comments, social_facebook_comments) and from social_youtube itself.

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?

Boundaries are clear: one video only, first page only, reply threads and later pages explicitly not returned, and comments-disabled yields an empty list. It stops short of naming an alternative route for reply threads or deeper pagination, so the agent knows what this tool won't do but is not told where to go instead.

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