List shared negative keyword lists

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

Annotations declare readOnlyHint=true, and the description reinforces that it only lists existing lists without side effects. Adds return value details (ID, name, status, keyword count) but does not mention error conditions or limits; however, these are less critical for a read-only operation.

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 concise sentences, front-loaded with the main action and outcome. No fluff, clear structure with the second sentence providing a pragmatic call-to-action.

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 simple read tool, it covers the core purpose, return fields, and a critical usage rule. It omits explanation of the customer_id parameter and does not formally define the output schema, but those are minor gaps given the breadth of context provided.

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 has no description for customer_id (coverage 0%), and the tool description does not explain that parameter. The meaning is likely inferable from context (Google Ads account ID), but the description adds no explicit guidance, leaving some ambiguity for an agent.

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 'List' and resource 'shared negative keyword lists (SharedSets) in the account', and lists the returned fields (ID, name, status, keyword count). Clearly distinguishes from sibling tools by name and 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?

Explicitly instructs to always call this before propose_negative_keyword_list to avoid duplicates, providing clear use-case guidance. Does not explicitly differentiate from other list-related tools like get_negative_keywords, but the primary usage rule is strong.

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