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

Annotations already declare it read-only, idempotent and non-destructive, yet the description adds real behavioral substance: the meaning of ad_strength values (PENDING through EXCELLENT), what action_items contains, and the non-obvious fact that an ad with all 15 headlines can still score low due to repetition. This goes well beyond what the structured fields convey.

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 platform scope and payload summary, then the two explanatory paragraphs about ad_strength and action_items. The detail is justified but the ad_strength paragraph is slightly discursive; a tighter sentence could carry the same distinction.

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 return values need not be spelled out, yet the description still clarifies the semantics of the two most interpretation-heavy fields. Platform scope, filters, and field meaning are all covered — nothing an agent needs to call it 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?

Schema description coverage is 0%, so the description carries the load and does it well: it defines customer_id as a 10-digit Google Ads id and identifies ad_group_id and ad_id as the two filter keys. It does not state whether the two filters are mutually exclusive or how they combine, leaving one small gap.

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 and resource ('reads the full content of Google Ads ads') and enumerates exactly what is returned (RSA headlines/descriptions, URL, status, ad_strength, action_items). The opening 'GOOGLE ADS ONLY' scopes it against the many sibling list/get tools for other platforms.

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?

Explicitly routes non-Google cases to list_meta_ads / list_tiktok_ads / list_linkedin_creatives, and explains the filter modes (ad_group_id or ad_id). It justifies the tool against an implied 'weak-ads list' but never names a specific Google sibling to prefer or avoid, so the when-not guidance is platform-scoped rather than tool-scoped.

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