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

Annotations already declare readOnlyHint=true and destructiveHint=false, so the safety profile is covered. The description adds real behavioral information by disclosing the dual mode of the call (catalogue of lists + campaign usage, versus keyword contents of one list), which an agent could not infer from the schema alone. It stops short of noting pagination, result limits, or how folder-level fan-out affects the response.

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?

A single sentence with zero filler, front-loading the primary verb and resource before the qualifiers. Each clause carries distinct information (lists, campaign usage, single-list keywords), so nothing could be cut without losing meaning.

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 read-only, four-parameter tool with no output schema, the description covers the essentials: what is returned and how list_id changes the result. The remaining gap is ambiguity about whether passing list_id restricts the payload to keywords only or augments the full catalogue, plus no mention of multi-account behavior.

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 only undocumented parameter is list_id, whose semantics the description does explain as selecting one list's keywords. That partly compensates for the gap, but the description adds nothing about how folder and account interact (aggregate vs single-account scope) or that language only affects card rendering, leaving it at the baseline-plus level.

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?

Uses a specific verb ('List') with a clearly named resource ('shared negative keyword lists') and spells out the three data categories returned: lists, campaign associations, and keywords for a given list. It never names the near-identical sibling google_ads_negative_list (singular) or the add/remove negative keyword tools, so the boundary between this and those siblings is left to inference.

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?

Usage is only implied: the parenthetical '(list_id)' hints that supplying the id switches the call into keyword-listing mode. There is no explicit when-to-use guidance, no statement of when to prefer google_ads_negative_list or google_ads_keywords, and no note on choosing folder vs account for multi-account clients.

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