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

The description usefully adds the credit-cost warning and the scan-scoped empty-result semantics, which are not in the annotations. However, annotations declare destructiveHint=true, readOnlyHint=false, and idempotentHint=false, yet the description frames the tool purely as passive intelligence gathering and never explains what side effect (e.g., a 'refresh' rescan invalidating cached data) makes it destructive. That omission on a non-read-only tool caps this at 3.

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?

Front-loaded with the highest-value fact (what data you get), then usage guidance, then the caveats. It is dense and mostly earns its length, though the capitalized ad-creative emphasis and the list of returned payloads run slightly long for what the output schema could carry.

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?

An output schema exists, so describing return payloads is a bonus rather than a requirement, and the credit-cost and empty-result caveats are genuinely helpful. But with 5 undocumented parameters and unexplained destructive behavior, the description leaves real gaps for a non-read-only, credit-consuming call.

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 coverage is 0% across 5 parameters with no descriptions anywhere. The description only faintly hints at location/language ('THIS scan of that location/language') and never clarifies the required target, the limit default, or what refresh=true actually does. For a fully undocumented schema, the description does not compensate.

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 a precise verb+resource — competitor paid-search keyword and ad intelligence for a domain — and enumerates the concrete payloads (bid keyword count, spend estimate, keyword list with volume/CPC, ad headlines/descriptions, landing pages). An agent can distinguish this from siblings like seo_ranked_keywords or competitor_ads without opening any schema.

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 clear when-to-use guidance: 'before writing your own RSAs' and 'to find keywords a competitor pays for that you could win organically,' plus a strong caveat that an empty result means no ads in this scan, not that the domain never advertises. It stops short of naming which sibling tool to use when you want your own ranked keywords or organic gaps, so it doesn't reach a 5.

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