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

Annotations only cover safety (readOnly, idempotent, openWorld); the description adds genuinely new behavioral facts: ~20 comments per page, two sort orders, cursor-based page traversal, 1 credit per page, and zero cost when comments are disabled. These are exactly the traits an agent needs before calling.

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?

Two tight sentences with zero filler, front-loading the return payload, then pagination, then cost. Every clause conveys actionable 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?

No output schema exists, so the description compensates by naming the returned fields (author, likes, reply count) and explaining pagination and cost. An agent has everything needed to call it correctly and interpret the result.

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%, so all four parameters are already documented, including the dual role of replies_cursor. The description only restates default sort and cursor usage plus the page size, adding marginal meaning beyond the schema, so the baseline 3 is right.

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 ("Returns a YouTube video's comments") and immediately scopes it with pagination size and ordering. This is clearly distinguishable from siblings like get_transcript, get_video_details, or get_video_heatmap without opening any 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?

Explains how to proceed for reply threads ("Pass a comment's replies cursor to read its replies") and notes the default ordering, giving clear operational context. It does not name explicit when-not-to-use conditions or point at an alternative sibling, but there is little overlap risk given the sibling set.

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