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

Annotations already declare readOnlyHint=false, destructiveHint=false, idempotentHint=false, so the description need not repeat these. The description adds valuable context on failure modes (budget requirements, optimization_goal matching, promoted_object requirements), which is beyond annotations. However, it doesn't disclose the return format or what happens on invalid input, which is acceptable given the detailed usage rules.

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 multi-paragraph but front-loads the core action and follows with actionable bullet points. Each sentence adds value, such as 'Budgets in cents' and the budget requirement. It is not overly verbose given the complexity, though it could be more structured with clear sections.

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 (19 parameters, 0% schema coverage, no output schema, no annotations), the description does an excellent job covering the most challenging aspects: budget constraints, optimization_goal compatibility, and promoted_object requirements. It also mentions bulk support and the flattened action. It does not cover all parameters but focuses on the ones likely to cause errors, which is sufficient for a competent agent.

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 for 19 parameters. It provides detailed semantics for targeting (JSON structure), budgets (in cents, requirements), optimization_goal (specific mappings), promoted_object (format for pixel and page), and destination_type (only for non-website). However, not all parameters (e.g., bid_amount, bid_strategy, status, start_time) are explained, but the description covers the most critical ones.

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 explicitly states 'Create or update Meta Ads ad sets' with a detailed list of actions (create, update) and resources (campaign, targeting, budget, schedule). It clearly distinguishes itself from siblings like meta_ads_adset_delete and meta_ads_adset_write_update by naming the destructive delete operation and noting that update is covered here.

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 when-to-use guidance, such as the critical rule about budgets: 'the ad set REQUIRES daily_budget or lifetime_budget, UNLESS the parent campaign already carries the budget' and when to omit budget. It also states when NOT to use this tool ('For destructive delete use meta_ads_adset_delete') and provides conditional requirements for optimization_goal and destination_type.

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