ads_ad_copy

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

With no annotations provided, the description carries the full burden. It explicitly declares the operation is read-only and states what it does and does not read. It also explains that it reports the actual policy topics behind limited/disapproved statuses, going beyond the status word. While it doesn't mention potential pagination or performance limits, the description is transparent about its core behavior and limitations.

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?

The description is about 60 words and packs every sentence with distinct value: the first explains the core read scope, the second addresses duplicate headlines, and the third clarifies exclusions and read-only nature. It is efficient and front-loaded, though slightly dense. No filler or tautology.

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?

The tool has an output schema, so return values are already structured. The description covers the essential info an agent needs: what is read, what is excluded, and the read-only nature. It could mention edge cases like pagination or how omitted filters behave, but the schema covers parameter behavior. Overall it is sufficiently complete for a read tool with a rich output schema.

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 each parameter (adId, adGroup, includeRemoved) already has a clear description. The tool description itself adds no parameter-specific meaning—the details about 'for reading back the copy' and 'answers whether a headline is repeated across ad groups' appear in the schema, not the description. Per the rubric, high schema coverage sets a baseline of 3, and the description does not exceed it.

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 opens with a clear verb ('Read') and a specific resource ('what a Google Ads ad actually says'), then enumerates exactly which details it covers (headlines, descriptions, pinning, performance labels, URLs, policy topics). It also explicitly states what it does NOT read (assets like sitelinks), which distinguishes it from the sibling ads_assets. This gives an agent a precise, unambiguous picture of the tool's 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?

The description provides contextual guidance: it notes that duplicate headlines are reported because they indicate poor A/B testing, and it clarifies that assets are not covered (implying use ads_assets for those). It also labels itself 'read-only', steering away from update tools. However, it does not explicitly name alternative tools such as ads_ads or ads_assets, so an agent would need to infer the comparison from the sibling list rather than being directly told when to use each.

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