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

Annotations already flag destructive=true, but the description adds the operationally critical facts beyond them: deletion cascades to adsets and ads, is irreversible, and success is only claimed when Meta confirms (deleted=True requires success=true), with error surfaces delete_failed and meta_api_error. This is exactly the context an agent needs before calling a destructive 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?

Front-loaded with the destruction warning, followed by the safer alternative, confirmation semantics, and ID constraints — a sensible priority order with no filler sentences. There is minor redundancy in restating the confirmation rule ('nichts gilt als gelöscht, was Meta nicht bestätigt hat').

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?

Output schema exists, yet the description still summarizes the decisive result fields (deleted, error=delete_failed / meta_api_error) so the agent knows what confirmation looks like. Combined with the cascade scope and cross-account guard, nothing needed to invoke this destructive tool correctly 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 coverage is 0%, so the description must carry the load — and it does for both parameters: workspace is described as the client workspace slug, optional when only one workspace exists, and campaign_id is constrained to the workspace's own ad account. It does not state the ID format/type explicitly, which keeps it short of a 5.

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 ('Meta-Kampagne endgültig löschen') plus the cascade scope ('inkl. Adsets/Ads') and irreversibility, so the agent knows exactly what is removed. It also names the sibling it is not — meta_update_campaign with status=PAUSED/ARCHIVED — making it distinguishable from the update tools 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 states when NOT to use it ('zum bloßen Stoppen besser meta_update_campaign mit status=PAUSED (umkehrbar) oder ARCHIVED') and gives the reversibility condition that selects the alternative. It also gives a hard precondition: the IDs must belong to the workspace's ad account, otherwise foreign_object.

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