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

Annotations already declare destructiveHint=true and openWorldHint=true, but the description adds the human-in-the-loop preview/confirm gate, which is genuinely new behavioral context. It omits whether deletion is permanent/irreversible and whether deleting a campaign cascades to its adsets and ads — meaningful gaps for a destructive operation.

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?

Two sentences, no filler. The destructive scope is front-loaded and the confirm protocol follows immediately, in the order the agent needs it.

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 tool with seven parameters and no output schema, the definition covers the confirmation workflow but not the consequences: irreversibility, cascade behavior, or what the preview call returns. An agent could execute the flow correctly yet still be unable to warn the user accurately about impact.

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?

With only 43% schema coverage, the description usefully explains two otherwise undocumented params: `confirm` as the execution flag and `confirm_name` as an exact-name match check. However, it says nothing about `id_or_name` (whether an ID or a display name is accepted, or how ambiguity is resolved) — a required parameter left entirely to the schema.

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 (Delete) plus the exact resources (campaign, ad set, ad, custom audience), matching the `level` enum. An agent can distinguish it from siblings like meta_rename, meta_set_status, meta_duplicate, and meta_delete_rule 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?

Gives an explicit two-step protocol: call first without `confirm` to preview, then call again with `confirm=true` and the matching `confirm_name`. That is strong when-to-use guidance for this tool. It stops short of naming alternatives — e.g. when to pause via meta_set_status instead of deleting — so it is not a full 5.

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