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

Annotations cover the safety profile (readOnlyHint=true, openWorldHint=false), so the agent knows this is a safe read. The description adds the comparison baseline ('prior equal window'), which is a useful behavioral detail about how decay is computed. But it doesn't touch on permissions, cost/auth context, pagination, or output structure. With annotations carrying safety, 3 is fair – some added value, notable gaps.

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?

One dense, front-loaded sentence with no waste. It states the resource and comparison basis efficiently. Too terse for the tool's complexity, but as raw conciseness it's strong.

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 17-parameter tool with 0% schema coverage and no parameter disambiguation, the description is drastically under-specified. The output schema exists so return values needn't be explained, and annotations cover safety, but parameter handling is a major gap. The comparison-window detail is the only substantive content; everything else an agent needs to invoke correctly 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?

17 parameters with 0% schema description coverage, and the description provides zero parameter meaning. No mention of url, days, date_from/date_to, range_preset, campaign_name, ad_account, user_id, page_id, etc. Many params appear overlapping (url/site_url, date range fields), which is exactly the situation where description must disambiguate – and it does nothing. Critical failure.

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 resource (Google Ads campaign fatigue) and metric (CTR/CPA/ROAS decay vs prior equal window), so the agent knows what the tool returns. However, it doesn't distinguish itself from sibling fatigue tools like meta_ads_get_fatigue or meta_insights_get_fatigue beyond the 'Google Ads' prefix, and the title already conveys that. Purpose is clear but differentiation from siblings is weak.

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 alternatives named, no conditions. The comparison window is implied but the agent isn't told when to choose this vs google_ads_get_trends or the meta fatigue siblings. Just a purpose statement, no usage framing.

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