meta_ads_audiences_create

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

With no annotations provided, the description carries the full burden of behavioral disclosure. It clearly states the operation is 'Mutating — not automatically reversible' and advises recording before-state with mureo_state_action_log_append for rollback. It also discloses the return value and notes that the customer list upload path is handled out-of-band. It does not mention auth needs or rate limits, but the side-effect and rollback disclosure is substantial 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?

Four sentences, front-loaded with purpose and return value. Every sentence adds meaningful information: mutation warning, subtype behavior, lookalike alternative. No fluff or redundancy.

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?

Given 8 parameters with 100% schema coverage and nested objects, the description covers the essential operational context: what it does, what it returns, that it mutates, how subtypes alter behavior, and which alternative to use for lookalike. No output schema exists, but the return value is stated. The description plus schema are sufficient to invoke the tool correctly.

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 description does not need to repeat parameter documentation. It does add some contextual glue to subtype behavior (e.g., WEBSITE auto-generates a PageView rule, CUSTOM accepts list upload) that goes slightly beyond the schema, but most parameter semantics are already well-covered by the schema. This meets the baseline for high coverage.

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 and resource: 'Creates a Custom Audience in a Meta Ads account.' It also states the key return value ('Returns the new audience_id') and distinguishes itself from the lookalike sibling by explicitly naming meta_ads_audiences_create_lookalike for similarity-expanded reach. This makes the tool's purpose unmistakable and differentiated.

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 provides explicit guidance on when to use this tool versus the lookalike alternative: 'For similarity-expanded reach use meta_ads_audiences_create_lookalike on top of this audience.' It also explains subtype-specific requirements (WEBSITE needs pixel_id+rule, CUSTOM accepts rule or list upload), giving clear direction on parameter usage. This qualifies as explicit when/alternatives.

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