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

Annotations already declare readOnlyHint, idempotentHint, and openWorldHint, so the safety profile is covered and the description is free to add analytical context. It does add genuinely useful interpretation guidance — benchmark thresholds such as Hook Rate >25% strong / <15% weak and Hold Rate >70% strong / <50% weak — which an agent cannot infer from the schema. It stops short of disclosing rate limits, result caps, or what happens when no video creative exists in range.

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?

It is front-loaded with what the tool returns, then benchmarks, then use case, then parameter routing — a logical order with no filler sentences. It is dense but every clause carries information; the benchmark parentheticals are long yet load-bearing for interpretation.

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?

With no output schema, the description carries the return-value burden and does so by enumerating the metrics returned plus their strength thresholds. The one remaining gap is that it doesn't say how results are structured or whether per-ad rows versus aggregates change the response shape, though the aggregation levels are implied by the ID choice.

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 100%, so the baseline is 3, but the description adds real meaning by stating the selection rule: 'ad_ids (preferred) OR adset_id OR campaign_id,' including the aggregation implication of each. This mutual-exclusivity and preference ordering is not expressed in the schema itself.

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 names the exact resource (Meta video ads) and the specific metric family it returns: Hook Rate, Hold Rate, Completion Rate, ThruPlay Rate, quartile retention, and cost-per-view metrics. This is distinguishable from siblings such as get_ad_performance_by_placement or get_creative_fatigue_metrics, which cover different cuts of performance data.

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?

It gives concrete when-to-use framing — 'creative strategist analysis: diagnosing weak hooks, retention issues, winning ad breakdowns' — which tells the agent the analytical intent this tool serves. It does not name an explicit alternative or a when-not condition (e.g., when to prefer get_creative_fatigue_metrics or get_top_performers), so it falls short of a 5.

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