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

Annotations only declare readOnly/openWorld, and the description supplies the non-obvious behavior an agent could not infer: private accounts return a shell with isPrivate: true instead of an error, that result should not be retried as a failure, the call costs 1 credit, and total likes live in `raw` rather than `viewCount`. This is exactly the kind of semantic and cost context the annotation layer does not carry.

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?

Five tight sentences, each carrying distinct information, with the field list front-loaded right after the lead. The conversational aside ('That is a real answer, not a failure') is slightly informal but earns its place by preventing a false-negative read of private accounts.

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 takes on the return-value burden by enumerating the profile fields and flagging the `raw` hearts caveat. The remaining hole is `cache_max_age`, left undefined by both schema and description, and there is no cross-reference to the many adjacent tiktok profile-ish siblings.

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 50%: `handle` is well described in the schema (accepts @handle or full URL) but `cache_max_age` is entirely bare in both schema and description. The description adds nothing about either parameter, so it neither compensates for the gap nor contradicts the schema; baseline 3 applies.

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 second sentence names the resource precisely and enumerates the returned fields (followers, following, video count, bio, bio link, verification, region), so an agent knows exactly what it gets back. The lead phrase 'Profile details' is a near-tautology and the description never contrasts itself with close siblings like tiktok_followers or tiktok_profileRegion, which keeps it off a 5.

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?

There is no explicit when-to-use or when-not-to-use guidance and no routing to alternatives such as tiktok_userShowcase, tiktok_followers or tiktok_profileRegion. The private-account sentence describes an outcome, not a usage condition, so selection still has to be inferred from the tool name.

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