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

With no annotations, the description carries the burden well: it discloses ordering ('newest first'), page size ('about 50 a page'), billing ('costs 3 credits, cached or not'), and failure handling ('a failed call is refunded'). It omits auth requirements and rate limiting, which are the main remaining behavioral unknowns.

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 dense sentences, front-loaded with the action and mode switch, then usage, then invocation constraint and cost. No filler or restatement of the title.

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 must describe the return shape, and it does ('each a profile with its follower and video counts'), along with ordering, pagination size, cursor propagation, and cost/refund behavior. Nothing essential for a correct call 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 value on top: the exclusive-or rule between `username` and `url` is not expressed anywhere in the schema (both are optional, no oneOf), and the `type` behavior plus page-size/pagination context clarify `cursor` usage.

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?

Names a specific verb and resource ('Fetch an account's followers'), covers both modes via `type=following`, and disambiguates from siblings like get_tiktok_profile or get_x_followers by stating the exact returned entity (profiles with follower and video counts). An agent can distinguish it from search_tiktok and the other TikTok tools without opening the 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 concrete use cases ('see who an audience is, or who a creator watches') and an invocation constraint ('Give exactly one of `username` or `url`'). It stops short of naming alternatives or when-not-to-use conditions, so it is clear context without explicit routing.

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