Datamanager.Audience.Upload Members

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

With no annotations at all, the description carries the full burden; it does disclose two meaningful constraints (SHA-256 hashing/normalization of identifiers, EEA consent requirement) that the agent could not infer from the schema. However it omits critical mutation behavior: what "guarded" means, whether the call is destructive/append-only, whether partial failures roll back, and any rate/batch limits.

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?

Two dense sentences, front-loaded with the action and immediately followed by the two hardest constraints. No filler, though "(guarded)" spends words without conveying information.

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 nested, 5-parameter, annotation-free mutation tool, the description leaves too much out: confirmation semantics, audience/destination identifier sourcing, batch size expectations, and failure behavior. The presence of an output schema excuses return-value explanation but not these input-side gaps.

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% across 5 parameters (4 required, nested members objects), so the description must compensate and largely does not. It explains only the identifier format for `members` and the EEA meaning of `consent`; `confirm`, `destination_id`, and `audience_id` remain completely undocumented, with `confirm` being the most consequential omission for a gated write.

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 ("Upload Customer Match audience members") and implicitly contrasts with the sibling remove_members via the verb. The parenthetical "(guarded)" is undefined jargon that adds no discriminating information.

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?

It supplies one real usage precondition (consent required for EEA) but never says when to choose this over alternatives, nor when the operation should be avoided. Nothing explains that `confirm` gates execution or what value it expects.

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