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

Annotations already flag destructiveHint=true and openWorldHint=true; the description adds genuinely new behavioral facts – the response confirms per-ad status, a lingering effective_status=WITH_ISSUES is review history rather than a live ad, and foreign IDs return {'error': 'foreign_object'}. That is real operational context the annotations cannot carry.

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 purpose and the bulk/validate_only guidance before the caveats. The WITH_ISSUES paragraph is a bit long and the mixed German/English key names add mild parsing friction, but every section still carries useful information.

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?

An output schema exists, so return-value detail is optional; the description still usefully explains what a success means and how to interpret a stale effective_status. For a destructive mutation tool the remaining gap is the ad_id/ad_ids conflict rule, which an agent could plausibly get wrong.

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 0% schema description coverage the description must compensate, and it does: it defines the status value set (absent from the schema, which is a bare string), explains ad_ids as the bulk path, and clarifies validate_only and the optional workspace. The one gap is the relationship between ad_id and ad_ids (exclusive? which wins if both sent).

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 ('Status einer oder MEHRERER Meta-Ads ändern') and enumerates the exact target states (ACTIVE/PAUSED/ARCHIVED/DELETED). This clearly separates it from meta_update_adset, meta_update_campaign and the Google-side ads_update_ad_status sibling.

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 concrete routing guidance: use ad_ids for bulk ('pausiere alle 22' ist EIN Aufruf) and validate_only for a dry run, plus a clear when-not clause about foreign-account IDs. It does not name sibling alternatives (e.g. meta_delete_campaign vs. status=DELETED), which keeps it out of 5 territory.

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