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

With no annotations, the description carries the full burden and does so well: it discloses the returned fields, warns that follower bounds, verification and sorting apply only to the current page rather than all matching creators (a genuinely non-obvious semantic), and instructs continued paging via nextCursor/searchId even when filters empty the page. That last note is exactly the kind of edge-case behavior an agent would otherwise get wrong.

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 tight sentences with no filler; the core purpose leads, the sibling routing comes second, and the caveats about page-scoped filtering and pagination are grouped at the end where they belong. Every sentence carries information the agent needs.

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 an 8-parameter search tool with no output schema and no annotations, the description covers purpose, return shape, alternative tool, pagination contract and a subtle filtering-scope caveat. An agent has everything required to call it correctly and interpret the result.

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 schema already documents count, cursor, search_id, min/max_followers and verified_only. The description adds meaning beyond the schema by explaining that these filters are page-scoped and by tying cursor to nextCursor/searchId, though it does not clarify the count 1-20 vs maximum 50 mismatch or the maxLength on non-string-ish fields.

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?

Specific verb + resource ("Find TikTok accounts matching a keyword") with the entity types named (creators, brands, competitors) and an explicit enumeration of what comes back (handle, nickname, followers, likes, verification). It is clearly differentiated from the video/hashtag/search siblings by operating on accounts, and it names creator_profile as the drill-down companion.

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 (build creator lists, size competitors, find partners in a niche) and routes to creator_profile for deeper profile data. It stops short of saying when NOT to use it versus near-neighbors like search_all or user_profile, so it is clear context rather than full when/when-not coverage.

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