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

Annotations already declare readOnlyHint=true and destructiveHint=false, so the safety profile is covered. The description adds genuine context by noting that ad status includes review/rejection states and that creative text, headline, and link are returned alongside period performance. It stops short of describing result volume, pagination, or default scoping behavior.

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?

Two dense sentences with no filler; the returned-field inventory is front-loaded. The opening noun fragment is slightly awkward but remains efficient and information-rich.

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 read-only reporting tool with no output schema and 10 mostly optional params, the description covers the payload contents but omits the boundaries an agent needs: how it differs from meta_adsets/meta_campaigns/meta_creative_insights and whether output is per-ad rows. Adequate but with clear gaps.

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 70%, so the enumerated params (detail, date_range, language, account) are already well documented with defaults and semantics. The description clarifies that campaign and adset act as filters, which is a small value-add for the three undescribed params (campaign, adset, status). Baseline 3 is appropriate given the schema does most of the work.

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 enumerates what the tool returns (status incl. review/rejection, creative text, headline, link, period performance), which makes the resource identifiable, but it is a noun fragment with no verb establishing the action (list/retrieve ads). It also does not differentiate itself from close siblings like meta_adsets, meta_campaigns, meta_ad_preview, or meta_creative_insights.

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?

"Filter by campaign or ad set" hints at scoping but never says when this tool should be chosen over meta_performance, meta_breakdown, or meta_creative_insights. There are no when-not conditions and no prerequisites mentioned.

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