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

With no annotations at all, the description carries the full burden and does so well: it discloses destructiveness, the cascading scope (contacts and source file), and irreversibility. It does not mention permission/ownership requirements or what the response returns, which keeps it just below the top mark for a zero-annotation 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?

Three short sentences, each carrying a distinct and load-bearing fact: scope, irreversibility, prerequisite. The danger signal is front-loaded with 'Permanently' and 'NOT reversible' before the procedural constraint.

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 single-parameter destructive tool with no annotations and no output schema, the description supplies everything needed to call it safely: what is destroyed, that it cannot be undone, and the approval precondition.

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% and there is only one parameter (`id`, documented as a UUID in the schema), so the description adds nothing about parameters. Baseline 3 applies when the schema does all the work.

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 audience') and immediately scopes it against its sibling delete_custom_audience_contact by saying the whole audience plus contacts and source file go. An agent can distinguish this from the single-contact delete and from preview_delete_custom_audience without opening a 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?

Explicitly names the prerequisite tool (`preview_delete_custom_audience`) and the human-approval gate that must precede this call, which is exactly the when-to-use condition an agent needs for an irreversible action. No alternative path is left ambiguous.

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