add_users_to_audience

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

With no annotations, the description carries the behavioral burden, and it does so well by disclosing the critical privacy behavior: values are normalized and hashed with SHA-256 locally, and Meta never receives plaintext data. It does not mention idempotency, error behavior, or rate limits, but the most consequential side effect and privacy guarantee are explicit.

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 short and front-loaded: purpose first, then schema hint and hashing behavior, then the GDPR guardrail. Every sentence earns its place, and there is no redundant repetition of the input schema.

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 3-parameter mutation tool with an output schema present, this description provides enough to invoke it correctly: the audience to modify, the accepted schema identifiers, and the data-handling behavior. Minor gaps, such as exact formatting rules for phone/email values and a direct statement that `values` must match `schema`, prevent a perfect score.

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 usefully enumerates the allowed `schema` values (EMAIL, PHONE, FN, LN) and implies what `values` should contain by stating those values are normalized and hashed. However, it does not describe `audience_id` or explicitly state that each value in the array must correspond to the chosen schema.

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 opens with a specific verb and resource: 'Ajoute des personnes à une audience personnalisée.' This clearly names the operation and distinguishes it from sibling tools like create_custom_audience, remove_users_from_audience, and audience lookup tools.

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 intended use case is clear from the purpose statement, and the GDPR note adds a legal precondition. However, the description does not explicitly state when to prefer this tool over alternatives or when not to use it, leaving the agent to infer comparisons from the tool name and sibling list.

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