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

Beyond the bare annotations, it discloses live screening, the screening criteria (recent posts reaching 5k+ views, posting activity, newest post), relevance judging from bio/captions, the known/profileId flag, and that accounts are never crawled or added automatically. It also exposes the 25-credit pricing and refund behavior; none of this contradicts the annotations (readOnlyHint=false, openWorldHint=true, idempotentHint=false, destructiveHint=false).

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 description is front-loaded with the discovery purpose and packs a lot of operational detail into one dense paragraph. The only real redundancy is stating the credit cost twice ('Priced up to 25 credits...' and 'Cost: 25 credits per call.'), which a bulleted structure would clean up.

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 six-parameter tool with no output schema, it covers what output means (ranked, recommended, known with profileId), the screening behavior, seed options, the no-auto-crawl rule, and pricing. It does not fully specify output fields or clarify how the optional seed parameters interact when more than one is provided, but the schema and description together are largely sufficient.

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 already high (83%), so the description doesn't need to re-document properties, but it adds a seed-relationship layer: handle/hashtag/search phrase are framed as alternative starting points and topic is explained as the relevance override. This is useful context beyond the schema, but some of it duplicates property descriptions.

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 opens with 'Discover new creators on TikTok, Instagram or YouTube from one seed' and specifies handle, hashtag, or search phrase, so the verb, resource, and input mode are unambiguous. It also contrasts itself with search_profiles and crawl_profile, making it distinguishable from its closest siblings.

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 explicitly says this is not for looking up a known creator and names search_profiles as the alternative, and it says to call crawl_profile when you actually want accounts added or crawled. It also tells the caller to pass topic to define relevance, giving actionable selection guidance.

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