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

With no annotations, the description carries the behavioral disclosure burden. It clearly indicates this is an export/creation action producing a saveable audience, which is useful. But it does not disclose side effects such as duplicate behavior on repeated runs, whether an existing audience is overwritten, or what response/confirmation the caller receives.

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 a single sentence that front-loads the action, clearly expresses the optional filters, and states the outcome. There is no filler or redundant restatement of the tool name.

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 description is sufficient for an agent to understand what the tool does and when to select it. It is not fully complete for invocation because the 'name' parameter is unexplained, and with no output schema or annotations, important behavioral details like return values and side effects are missing.

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 0%, so the description must compensate. It successfully maps search_id to the source search and roles/only_with_email/ids to optional filters. However, it does not explain the 'name' parameter, which is likely needed to label the resulting audience.

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 states a specific operation: taking personas matched by a Signal Search and exporting them into a custom audience. It clearly identifies the resource produced, 'custom audience', and the downstream purpose, 'attached to any campaign', which distinguishes it from export-to-CSV siblings like sdr_export_people_csv.

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 gives clear context: use this when you have a Signal Search and want to turn matched personas into a reusable audience. It also notes optional filters. However, it does not explicitly name alternatives or state when not to use this tool.

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