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

With zero annotations, the description carries the full burden and does so: it discloses a real cost (1 credit per contact actually enriched, charged as it runs), the asynchronous/background execution model, and the external side effects (email, phone, LinkedIn, WhatsApp lookups). This is exactly the risk information an agent needs before spending money.

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?

Three tight sentences, front-loaded with the credit-spend warning ('SPENDS CREDITS' in both title and first words), then the mechanism, then the workflow. No filler or repetition.

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 an async, credit-consuming mutation with no output schema, the description supplies everything needed: cost model, background nature, prerequisite approval step, polling tool, and stop tool. An agent could execute the full lifecycle correctly from this text alone.

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?

Only one parameter (`id`) with 100% schema description coverage, so the schema already documents it as a custom audience UUID. The description adds no syntax, format, or constraint details beyond that, which is the expected baseline when the schema does the work.

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 (starts background enrichment) on a specific resource (not-yet-enriched contacts in a custom audience) and enumerates the lookup types covered. It also implicitly distinguishes itself from its preview/poll/stop siblings via the workflow language, so an agent can tell it apart without reading schemas.

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 gates invocation: 'Only call after the user approved `preview_enrich_custom_audience`.' It then names the follow-up alternative (`get_custom_audience_enrichment` for polling) and the exit path (`stop_custom_audience_enrichment`), covering when to use, what to use next, and when to stop.

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