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

With no annotations, the description carries the whole burden and does it: it declares the operation permanent and not reversible, explains that the reason string is logged to improve automatic selection, and imposes a precondition on a specific preview tool. That is the destructive-action context an agent needs before invoking.

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 short sentences with the irreversible warning front-loaded, followed by reason semantics and the prerequisite. Every sentence adds distinct information and none restates the title.

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?

Covers the destructive nature, the reason field's valid values, and the required prior approval step, which is sufficient for a three-parameter mutation with no annotations. It could mention what is returned or whether the removal affects audience counts, but no output schema exists so the omission is minor.

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 67% and the optional `reason` field has no enum in the schema; the description fills that gap by listing the UI choices (Not relevant, Wrong contact, Already a customer, Bad data, Other) and explaining the field's downstream purpose. It adds little about `id` or `contact_id`, but the schema already labels both as UUIDs.

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 and resource ('Permanently remove one contact from a custom audience') and makes the granularity explicit with 'one contact', which separates it from delete_custom_audience targeting the whole audience. An agent can identify the exact unit of work without opening the schema.

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?

Gives an explicit gating rule: 'Only call after the user approved preview_delete_custom_audience_contact', naming the sibling that must run first. This is a concrete when-to-call workflow condition, not implied guidance.

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