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

With no annotations, the description carries the full burden and does disclose the most important trait: 'Changes nothing' confirms it is a non-mutating read. It does not describe what the preview actually returns or whether it errors when the contact is absent, which matters given there is no output schema.

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, each earning its place: what it does, its safety property, and the workflow step. The safety claim and the human-review instruction are front-loaded.

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 preview tool this covers the essential decision points: no side effects and the human-confirmation step before the real delete. The gap is the shape of the preview output and the meaning of the optional reason parameter, which nothing else documents.

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%: id and contact_id are documented as UUIDs, but `reason` has no description anywhere. The description adds no parameter meaning at all, so the undocumented parameter stays opaque, though the schema carries most of the weight.

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 (dry-run of removing one contact from a custom audience) and explicitly names the mutation sibling it previews. An agent can distinguish it from delete_custom_audience_contact and preview_delete_custom_audience without opening either 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 workflow directive: run this, show the result to the human, then call delete_custom_audience_contact. The when-to-use and the alternative are both named rather than inferred.

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