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

No annotations are present, so the description must carry behavioral context. It adds one useful behavioral detail: listing includes 'public groups plus any organization-visibility groups your organization can access.' It does not disclose other behavioral traits like pagination behavior, rate limits, or idempotency, though this is a read-only list operation and the output schema covers return values.

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 front-loads the core definition in one sentence, then adds a compact two-bullet 'Use when' section. Every sentence earns its place: what the tool lists, why it matters, and how the result is used downstream.

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 list operation with all parameters optional and fully documented, the description provides enough context: what a source group is, what visibility scope is returned, and how the slug is consumed by submit_query. The output schema covers the return shape, so no additional return documentation is needed; a note on pagination would be the only minor gap.

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?

The input schema already documents page, api_key, and page_size with 100% coverage, so the baseline is 3. The description's mention of obtaining a slug for submit_query concerns output data rather than this tool's parameters, so it adds no direct parameter semantics.

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 first sentence states a specific verb ('List') and resource ('source groups'), and defines them as 'named domain allowlists,' which immediately distinguishes this from other list_* siblings. The 'Use when' bullets reinforce that this tool exposes reusable named sets of source domains, so an agent can identify it correctly.

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 includes an explicit 'Use when' section with two concrete conditions: discovering reusable named sets of source domains and obtaining a group's slug to attach to submit_query via source_groups. It does not list exclusions or alternative tools, but the target use cases are clear and unambiguous.

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