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

Annotations already declare readOnlyHint, idempotentHint, openWorldHint and destructiveHint=false, so 'read-only: returns public data and changes nothing' largely restates structured data. However, the pricing model — 1 credit per result, minimum 1 credit per request — is genuinely new and material information an agent needs before calling, which lifts this above the annotation baseline. It stops short of noting any rate limits or maximum pagination depth.

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 short sentences, front-loaded with the core purpose followed by safety and cost. Nothing is padded, and the pricing caveat is stated before an agent commits to the call.

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?

For a simple read tool with no output schema and fully documented parameters, the description covers purpose, safety, and cost. The main residual gap is return shape and how replies are paginated in practice, but the cursor parameter description carries the pagination contract.

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%, with count bounds (1–20, default 20), cursor semantics tied to nextCursor, and videoId accepting either a raw ID or a full URL all documented in the schema. The description adds no parameter meaning beyond that, so the baseline 3 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 (get) and a precisely scoped resource: replies to a single TikTok comment, keyed by commentId. This is clearly distinguishable from the sibling tiktok_get_video_comments, which lists top-level comments on a 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 when-to-use guidance, no mention that a commentId must first be obtained from tiktok_get_video_comments, and no alternative routing. The only usage-adjacent information is the credit cost, which tells an agent about expense but not about selection or sequencing.

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