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

Adds substantial context beyond the annotations: asynchronous job pattern (job_id returned, poll scrape_jobs_status), a data limitation (commenters returned as public usernames only), and billing semantics (max_results reserved, only actual count charged, 5P per result with a 10P base from 2026-11-06). The annotations only flag openWorld/idempotent/non-destructive, so the description carries real additional value. Consistent with readOnlyHint=false (it creates a billed job) and idempotentHint=true.

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 async/polling instruction and pricing note are front-loaded and useful, but the Korean sentences restate the same facts already given in English ('접수 즉시 job_id 를 돌려주며 결과는 scrape_jobs_status 로 조회합니다' mirrors the English), so not every sentence earns its place. Bilingual framing may be intentional for a Korean-titled tool, but it is still duplicated content.

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 correctly explains the return path (immediate job_id, later polling via scrape_jobs_status) and the billing model, which is what an agent needs to call it correctly. It stops short of describing the shape of the final comment payload beyond 'public usernames only', a minor gap for a creation tool.

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 url, max_results, and idempotency_key are already documented in the schema, and the description's mention of the reservation/charge behavior for max_results duplicates the schema text rather than extending it. Baseline 3 is appropriate; idempotency_key is not elaborated in the prose.

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+resource: 'Collect comments of a TikTok video (up to 100)', and immediately disambiguates against the sibling it depends on by naming scrape_jobs_status for retrieval. The scope limit and the fact that only public usernames are returned are stated up front, so an agent can tell it apart from tiktok_search_create/tiktok_video_create without opening a 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?

Gives clear operational context: the tool returns a job_id immediately and the caller must poll scrape_jobs_status for the result, which is exactly the workflow an agent needs. It does not, however, state when NOT to use it (e.g. versus the Instagram/X comment siblings) or any platform prerequisites, so it stops short of explicit alternatives/exclusions.

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