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

Annotations already establish the safety profile (readOnlyHint=false, destructiveHint=false, idempotentHint=false), so the description's job is smaller. It still adds real behavioral context by disclosing the dry-run/preview pattern via confirm, which is not visible in annotations and materially changes how an agent should invoke it.

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?

Three terse sentences with no filler; the core action, the location_ids constraint, and the confirm contract are all front-loaded and immediately scannable.

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 6-parameter mutation tool with 4 required fields and an output schema present, the description covers the non-obvious parameters and the preview/apply contract. Return-value explanation is unnecessary because the output schema handles it, leaving nothing an agent needs missing.

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%, so the description carries the burden for 6 parameters, and it delivers on the tricky ones: location_ids format (comma-separated) plus its source tool, audience_size enum values (NARROW|BALANCED|BROAD), and confirm semantics. advertiser_id, name, and source_audience_id remain undocumented but are largely self-evident.

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 specific verb+resource ('Creates a TikTok lookalike audience') and identifies the required input as a source custom audience, which separates it from TikTok customer-file or shared audiences. It never names a sibling tool explicitly, so an agent must infer that this is the TikTok counterpart to create_meta_lookalike_audience / create_customer_match_audience.

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 actionable operational context: location_ids must come from tiktok_region_search, and confirm=false previews while confirm=true applies, which tells the agent the safe call order. It does not state when to choose this tool over other audience-creation siblings, so it stops short of full alternative routing.

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