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

Annotations already declare readOnlyHint=true, destructiveHint=false, and openWorldHint=true, so the safety profile is covered. The description adds that the payload includes quality score components and performance metrics, and that the negatives flag swaps the result set entirely — useful behavioral context. It says nothing about pagination, default result volume (limit caps at 200), or how multi-account folders are resolved, which the agent must read from the schema.

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?

Two sentences, no filler, with the core payload description front-loaded and the mode switch second. Slightly awkward as a sentence fragment without a verb, and '(and its components)' is a parenthetical that could be folded in more cleanly.

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 eight optional parameters and no output schema, the description does the compensating work by enumerating the returned fields (match type, status, quality score components, bids, performance). Combined with the schema's account/folder/date descriptions, an agent has enough to call this correctly; only result volume and negatives-vs-sibling routing remain thin.

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 75%, and the one non-trivial undocumented parameter, negatives, is explained in the description as a result-set switch rather than a filter. The description also implies the account/folder scoping and date-range behavior is optional by presenting them as inputs to a listing. The remaining gap is limit, whose pagination semantics are documented nowhere.

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 resource (keywords) and enumerates exactly what each record carries: match type, status, quality score and its components, bids, and performance. It lacks an explicit verb ('list'/'retrieve'), so the agent must infer this is a read/list operation from the noun phrase, but the resource and payload are unambiguous.

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 only routing guidance is 'Set negatives=true to list negative keywords instead,' which covers the internal toggle but ignores the dedicated siblings google_ads_negative_list and google_ads_negative_lists. There is also no guidance distinguishing this from google_ads_keyword_ideas (research) or google_ads_search_terms (query data), which an agent could easily confuse with a keyword listing.

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