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

Annotations already declare destructiveHint=true, but the description goes further by specifying the exact failure modes and error codes (foreign_object, has_lookalikes with lookalike_audience_ids) and the post-delete warning if the audience is still readable. That is behavior an agent cannot infer from the annotation block.

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 irreversible nature and the account-scope constraint, and every clause carries operational weight. It is dense with parenthetical error codes, which is efficient but slightly harder to scan than a clean two-sentence structure.

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 destructive two-parameter tool, it covers preconditions, sibling handoffs, failure semantics, and even return fields despite an output schema existing. Nothing an agent needs before invoking the delete is missing.

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 must carry the load; it does by explaining that audience_id comes from meta_list_audiences and that workspace is a customer slug required only when multiple workspaces exist. The ID's expected format (numeric vs act_-prefixed) is still unstated.

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?

Names a specific verb and resource ('Custom Audience endgültig löschen') and immediately flags scope ('nicht umkehrbar'), which separates it from meta_create_audience and meta_list_audiences without opening any 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 routes the agent: get IDs from meta_list_audiences, reassign dependent adsets with meta_update_adset before deleting, and expect refusal when Lookalikes exist. These are concrete preconditions and named alternatives, not implied usage.

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