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

Annotations are minimal (all false/no hints), so the description carries the burden. It discloses significant behavioral constraints: budget requirement and CBO exception, lifetime_budget requiring end_time, optimization_goal-to-campaign-objective mappings, promoted_object requirements for specific goals, and destination_type restrictions. This goes well beyond the structured fields, giving agents necessary failure-avoidance 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 dense and well-organized with action bullets, a prominent BUDGET warning, and code-like examples. It is longer than the ideal 2-sentence description, but the complexity of the tool (19 params, multiple conditional rules) justifies the length; no filler sentences are present.

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 19-parameter create/update tool with no output schema and uninformative annotations, the description covers the most failure-prone areas (budget, optimization goal, promoted_object, destination_type) and bulk support. It doesn't describe return values or auth_account usage, but given no output schema and the exhaustive field-level rules provided, it is substantially complete.

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%, but the description injects semantics for the highest-risk parameters: targeting JSON format, budgets in cents, optimization_goal allowed values per objective, promoted_object structure, and destination_type applicability. Many remaining params (name, status, bid_strategy, billing_event) are either self-explanatory or constrained by enums, yet the description does not explicitly annotate all 19, so it's helpful but not exhaustive.

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 opening line 'Create or update Meta Ads ad sets' is a specific verb+resource statement. It enumerates actions (create linked to a campaign, update existing ad set) and explicitly points to meta_ads_adset_delete for destructive deletions, distinguishing from that sibling. The range of covered fields (targeting, budget, schedule) makes the scope 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 gives explicit alternative for delete ('For destructive delete use meta_ads_adset_delete') and provides field-level when-to-use guidance (e.g., destination_type only for non-website destinations, omit for website traffic; budget rules depending on campaign budget optimization). It does not explicitly contrast with meta_ads_adset_write_create, but the combined create/update nature and clear action list imply the context.

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