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

Annotations already flag destructiveHint=true, but the description adds meaning beyond them: deletion is permanent/irreversible, lookalikes must be removed before their source, a 'Pro' plan appears to be required, and confirm:true is mandatory. These are exactly the behavioral facts an agent needs before firing an irreversible write.

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 short sentences with zero filler, and the most consequential fact (permanent deletion) plus the ordering constraint are both front-loaded before the low-priority mechanics.

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 3-parameter destructive mutation with no output schema, the description covers permanence, dependency ordering, plan tier, and the confirm gate. It doesn't say what error surface the caller sees (e.g., failure when a source audience still has lookalikes), a minor remaining gap.

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 extra weight, and it does explain 'confirm' as 'Requires confirm:true'. However, audience_id and meta_account_id get no treatment at all; their names are largely self-explanatory, which keeps this at a minimum-viable 3 rather than lower.

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 and resource ('Permanently delete a custom or lookalike audience') and scopes exactly which audience types are affected. The named resource cleanly separates it from sibling deleters like delete_campaigns and delete_catalog_product without ambiguity.

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 an explicit ordering prerequisite ('Delete lookalikes before their source audience') and a hard gating requirement ('Requires confirm:true'), which is real directional guidance. It stops short of naming the sibling a caller would use first (e.g., list_custom_audiences) to obtain an audience_id.

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