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

Annotations only declare readOnlyHint and openWorldHint; the description adds meaningful behavioral detail beyond them: the two-tier data source (profile field first, recent posts as fallback), the explicit non-inference guarantee, and a 1-credit cost. It omits what happens when no region is determinable and says nothing about the cache behavior the schema exposes.

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?

Six short sentences, each load-bearing: what it returns, where the value comes from, what it is not, cost, and invocation. Front-loaded and free of filler.

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 should say what the response looks like (a bare region string? a code? an object?) and what is returned when TikTok publishes no region anywhere. It covers the sourcing logic and cost well but leaves the return contract and the degenerate case unaddressed.

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 67% and the schema marks zero required parameters, so the description's 'Pass either `handle` or `url`' is genuinely additive — it tells the agent one identifier suffices. However, the third parameter `cache_max_age` has no schema description and no mention in the description, so a third of the parameter surface is undocumented everywhere.

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?

States a precise resource — the market/region TikTok assigns a creator account — and disambiguates it from broader profile data by spelling out the exact data source (the `region` field, falling back to post-stamped region). It does not explicitly name a sibling tool it should be preferred over (e.g. tiktok_profile), but the scope is unambiguous.

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?

The description says to pass either `handle` or `url` and that the result is never inferred from language/timezone/content, which narrows expectations. But it gives no explicit when-to-use vs. when-to-use-a-sibling guidance — an agent must still decide on its own between this and tiktok_profile.

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