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

The description goes beyond the annotations by disclosing billing ($0.006 per page), page size (~12 videos), and the sentiment surcharge — cost and volume context an agent cannot get from readOnlyHint/openWorldHint. It stops short of rate limits, auth requirements, or failure behavior.

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 tight sentences: what it does and the identifier constraint first, then return-shape, then pagination/cost. No filler, no repetition of annotation-covered traits.

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, the description compensates by pointing to a sibling tool for the return field set and by covering pagination and cost. It's near-complete for a read endpoint, though an agent must look up tiktok_user_videos to know the actual fields.

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 the schema already documents all four parameters, and the description largely restates them (exactly-one rule, page size) plus one useful hint that music_id also appears on every video. That is a marginal add over structured data, so the 3 baseline applies.

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 ('Get the videos using a TikTok sound') plus the two accepted identifier forms, which cleanly separates it from siblings like tiktok_music_details (music metadata) and tiktok_hashtag_videos / tiktok_playlist_videos (other video sources). The explicit 'Returns the same video fields as tiktok_user_videos' cross-reference further disambiguates scope.

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 'provide exactly one' rule for url vs music_id is stated, which is genuine usage guidance, but no alternatives are named or excluded (e.g., when to prefer tiktok_music_details over this, or this over search_tiktok). Usage is implied by the resource rather than explained.

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