meta_ads_audiences_create_lookalike

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

With no annotations provided, the description carries the full burden and does so excellently. It discloses mutating side effects, non-reversibility, rollback suggestion, the 24–72h build delay, the fact that approximate_count remains 0 until build finishes, and the practical meaning of ratio values. This is rich behavioral context beyond what schema alone would tell the agent.

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 six sentences, each with a distinct purpose: purpose, return value, mutation warning, timing behavior, ratio semantics, and alternative tool. It is front-loaded and avoids redundancy. Every sentence earns its place, making it dense yet efficiently organized.

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 no output schema or annotations, the description covers the critical aspects: what it creates, what it returns, timing, ratio ranges, and rollback guidance. It is nearly complete, though it omits potential error scenarios (e.g., invalid source audience) and account_id fallback behavior, which are only in the schema.

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 100%, so the baseline is 3. The description adds extra value by interpreting ratio in concrete terms ('top 1% most similar users in the target country (smallest, highest match)') and giving a recommended source size (1,000–10,000 users). It does not rehash every parameter but clarifies the most behaviorally significant ones.

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 a specific verb+resource: 'Creates a Lookalike Audience from an existing source audience.' It also states the return value (audience_id), which clarifies the tool's core function. It is clearly distinguished from siblings like meta_ads_audiences_create (custom audience) and meta_ads_audiences_list (listing).

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 explicitly names an alternative for a different need: 'For the base audience list use meta_ads_audiences_list.' It also advises recording before-state with mureo_state_action_log_append for rollback, implying when to consider safety. However, it does not explicitly state when to avoid this tool or when a custom audience would be preferred over a lookalike.

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