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

Annotations already declare destructiveHint=true, readOnlyHint=false, and idempotentHint=false, so the safety profile is covered. The description adds real operational context beyond that: the ad-set-attachment blocker that will cause failure and the confirm=false preview/dry-run behavior. It does not state whether deletion is permanent/irreversible, which is a minor residual gap.

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 action and its key constraint, and most sentences are dense and actionable. The backstory sentence ('We could create audiences but never delete them, so bad ones piled up permanently') is motivational filler that does not help the agent act and could be cut.

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 destructive nature is covered by annotations. Combined with the precondition, preview mode, and ID source, the definition is nearly complete for a two-parameter destructive call; only reversibility/error behavior is left 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 description coverage is 0%, so the description carries the burden and largely meets it: it identifies the source of audience_id ('from list_meta_audiences') and explains the non-obvious semantics of confirm ('confirm=false previews'). It does not specify the ID format or explicitly state that confirm=true commits the deletion, leaving slight inference required.

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?

Opens with a specific verb and resource ('DELETES a Meta custom/lookalike audience') and narrows scope to Meta custom/lookalike lists, which separates it from delete_meta_ad, delete_meta_campaign, and delete_microsoft_audience. An agent can identify the target without opening the schema.

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 concrete when-to-use scenarios (mistaken builds, duplicates, privacy-request removal) and an explicit when-NOT precondition: an audience attached to an ad set cannot be deleted and must be detached first. It also routes the agent to list_meta_audiences for obtaining the ID.

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