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

Goes well beyond the annotations by disclosing that the ad group starts DISABLED (paused), the confirm=false preview / confirm=true apply gate, how automation=AUTO switches endpoints, Smart+ restrictions (real placement list required, targeting can be widened, pacing/search disabled), currency-derived budget minimums and that TikTok's error reports the exact minimum. This is unusually rich behavioral context for a mutation tool.

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?

Front-loaded with the essentials (creates ad group, starts paused, location_ids required), and most sentences carry parameter-specific value. But it is a single ~450-word wall of text with no bullets or grouping, making it hard to scan under a 29-parameter surface. Length is partly justified by complexity, but structure is weak.

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?

An output schema exists, so return values need not be described, and the description covers the conditional logic (billing events, promotion types, messaging paths, budget minimums, preview/apply) an agent needs to invoke it correctly. A few targeting-related parameters remain undocumented, leaving minor gaps for a tool of this complexity.

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 description coverage is 0% and there are no enums in the schema, so the description carries the full burden — and it largely does, enumerating allowed values for optimization_goal, billing_event, promotion_type, age_groups, genders, placements, bid_type, pacing, scheduling formats, and messaging_app_type semantics. However audience_ids, excluded_audience_ids, interest_category_ids and budget_mode are never explained, so it doesn't fully compensate for the gap.

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 opening sentence states a specific verb (Creates) and resource (TikTok ad group) plus the scope of what it configures (targeting/budget/billing event). The resource is distinct enough that an agent can tell it apart from create_tiktok_campaign, create_tiktok_ad and update_tiktok_adgroup without opening schemas.

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 rich conditional guidance: use optimization_goal=CONVERSATION for messaging ad groups, automation=AUTO to work inside Smart+ campaigns, confirm=false to preview. It also points to prerequisite/sibling helpers (tiktok_region_search for location_ids, create_tiktok_ad for whatsapp_number). It stops short of explicitly contrasting this tool with the sibling update_tiktok_adgroup or stating ordering vs create_tiktok_campaign, so not a 5.

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