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

Annotations already declare readOnly, idempotent, non-destructive, open-world behavior, so the safety profile is covered. The description adds genuinely new context: the returned fields, the ¥0.3 per-call cost, the fact that only successful calls are billed, and automatic refunds on failure or empty results — pricing and billing semantics no annotation conveys.

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 short sentences, front-loaded with purpose, then return fields, then usage/prerequisite, then billing. Every sentence carries information an agent needs; the billing sentence is the least essential but still affects invocation decisions on failure.

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 enumerating the returned fields, and it covers the prerequisite ID, the billing model, and the refund behavior. For a 3-parameter read tool with full annotation coverage, nothing material 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?

Schema coverage is 100%, so the baseline is 3, and the description adds real meaning beyond it: comment_id must specifically be a top-level/main comment ID, which the bare '评论ID' schema label does not clarify. media_id and the fallback _token remain purely schema-documented, so it is not a full 5.

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?

The description names a specific verb+resource ('获取Instagram评论的子评论') and pins the scope to second-level replies by listing the returned fields (正文、点赞数、回复者信息、时间). This implicitly separates it from ig_post_comments, but it never names that sibling as the source of the required comment_id, so an agent must infer the pairing.

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?

It states a concrete use case ('追踪评论区的二次讨论与争议点') and a hard prerequisite ('需先拿到主评论ID'), which tells the agent this cannot be a first call. It stops short of an explicit when-not or of naming ig_post_comments as the step that produces the prerequisite ID.

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