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

Annotations already declare readOnlyHint=true, destructiveHint=false and openWorldHint=false, so safety is covered. The description adds one genuine behavioral signal not in the annotations — that ranking runs on 'cached' performance data, implying possible staleness — but says nothing about sort direction, defaults, or what happens when no cached data exists for the window.

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?

A single front-loaded sentence with no filler; nothing wasted. It is efficient, but the brevity is achieved by omission rather than by disciplined compression of necessary detail.

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 an 8-parameter ranking tool with zero schema descriptions, the one-line description leaves the agent without enough to call it correctly — which metric wins, what min_spend filters, how product_ref/ad_account_id scope results, and whether results are per-media or aggregated. The output schema covers return values, but invocation context is missing.

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% across 8 parameters, including two enums (metric: roas/cpa/ctr/spend, media_type) and a const window, so the description must compensate and does not. 'By cached ad performance' only loosely gestures at the metric parameter; limit, min_spend, product_ref, ad_account_id and group_by_media_type are entirely unexplained.

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?

States a specific verb+resource ('rank reusable media') that maps onto the creatives_top name and implies a ranked-by-performance result, which an agent can distinguish from plain listing siblings like creatives_list. However, 'cached ad performance' is left unexplained and no sibling is named, so it stops short of full differentiation.

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?

There is no when-to-use guidance at all. With two adjacent siblings (creatives_list, creatives_pick) and performance-oriented siblings (insights_query_overview, products_get_top_campaigns), the description never says why an agent should pick this one or what precondition (e.g. existing cached insights) it needs.

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