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

Goes far beyond the annotations: it names specific failure modes (budget_conflict on daily+lifetime, end_time_required on adsets, bid_strategy_requires_budget), states that nothing is created on such failures, that bid_strategy cannot be changed on the campaign afterwards, that special_ad_categories is passed through unchecked, and that campaign end dates do not exist at Meta. This is exactly the behavioral context the readOnlyHint/destructiveHint 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?

The purpose sentence is front-loaded and each subsequent block maps to a parameter, so the structure is easy to scan. It is nonetheless dense and long; the bid_strategy paragraph in particular becomes convoluted with nested parentheticals pointing at meta_create_adset.

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 write tool with an output schema and partial annotations, nothing an agent needs to call it correctly is missing: creation defaults, budget-belonging rules, cross-tool dependencies (adset end_time, min_roas), failure behavior, and how to read the result back via meta_list_campaigns.

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 coverage the description has to carry all parameter meaning, and it does: enum values for objective, EUR semantics and CBO implications for daily_budget/lifetime_budget plus their mutual exclusivity, bid_strategy options and where bid_amount/min_roas actually belong, admitted status values, example literals for special_ad_categories, and the validate_only dry-run meaning. Only 'name' is left implicit, which is trivially obvious.

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?

Opens with 'Neue Meta-Kampagne anlegen' — a specific verb and resource — and immediately distinguishes it from meta_update_campaign (activation is a deliberate second step) and meta_create_adset (where adset-level budget lives). An agent can route to it 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 states the default PAUSED behavior and that activation is a separate, intentional call to meta_update_campaign. It also defines when bid_strategy is allowed (only with CBO), what to do otherwise (set it per adset), and the fallback when validate_only is wanted. Alternatives and exclusions are both named.

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