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

Annotations already declare readOnlyHint and openWorldHint=false, so safety is covered. The only behavioral detail added is that decay is measured 'vs the prior window' — the description doesn't say how the window is chosen, what entity level (ad, ad set, campaign) the fatigue is computed for, or what happens when history is too short.

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 clause that states the metrics and the comparison baseline with no filler. It is efficient, though the terseness is partly the reason key details are missing.

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 19 undocumented optional parameters and no explanation of what constitutes fatigue or which entity the analysis targets, the definition is far too thin for a tool of this complexity. The output schema covers return values, which offsets the gap slightly.

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?

19 parameters at 0% schema description coverage, and the description mentions none of them — not ad_account, days, date_from/date_to, range_preset, limit, or the many identifier params. 'Prior window' gestures at time scoping but gives no mapping to any parameter.

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 platform and the analysis (frequency plus CTR/CPA/ROAS decay vs. prior window), so the computation is identifiable. But the verb is implicit and nothing distinguishes it from the sibling meta_insights_get_fatigue or google_ads_get_fatigue, which appear to cover the same concept for a different scope.

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?

No when-to-use guidance, no exclusions, no mention of the near-duplicate siblings (meta_insights_get_fatigue, google_ads_get_fatigue, google_ads_get_fatigue's platform variant). The agent must infer selection from the platform prefix alone.

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