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

Annotations declare readOnlyHint=false, destructiveHint=false, and idempotentHint=false, which already indicate this is a mutating, non-destructive, non-idempotent operation. The description adds valuable context: budgets are in cents, campaign budget optimization means ad sets must not carry their own budget, and bulk support via campaign_ids. It does not contradict annotations. It could mention that updates are not idempotent, but the annotations already cover that, so the description adds sufficient extra context.

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 description is well-structured with a clear action list, objectives, budget notes, and a pointer to the delete tool. It is front-loaded with the main purpose. The 'Flattened action: create' line is a bit cryptic and could be confusing, but it's short. The bulk support note is useful. Overall, it's concise and organized, though the flattened action line adds little value.

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?

Given the tool's complexity (11 parameters, 4 actions, no output schema, no annotations beyond basic hints), the description covers the core semantics well: actions, objectives, budget units, and the critical budget optimization rule. It also mentions bulk support. However, it does not explain the return value or error behavior, and some parameters (bid_strategy, special_ad_categories) are not described. For a tool with this many parameters and no output schema, it is reasonably complete but not exhaustive.

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 compensate. It explains the meaning of 'budget' (in cents, with example), the relationship between campaign budget and ad set budgets, and the objective enum values are listed. It also clarifies that 'campaign_ids' enables bulk execution. However, it does not explain parameters like 'account', 'auth_account', 'bid_strategy', 'special_ad_categories', or the difference between 'daily_budget' and 'lifetime_budget', which are left to the schema. Given the 0% coverage, the description adds significant value but still leaves gaps.

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?

The description clearly states the tool creates, updates, pauses, or activates Meta Ads campaigns, with a specific verb and resource. It distinguishes itself from siblings by listing the four actions and explicitly pointing to meta_ads_campaign_delete for destructive deletes, and the sibling list includes separate pause/activate/update tools, making this tool's role as a combined write tool clear.

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?

The description provides explicit guidance on when to use this tool versus alternatives: it lists the four actions (create, update, pause, activate), notes that pause and activate are shortcuts, and explicitly says 'For destructive delete use meta_ads_campaign_delete instead.' It also explains the budget behavior (campaign budget optimization vs. per-ad-set budgeting), which is critical for correct usage.

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