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

The description reveals important behaviors beyond annotations: PII is SHA-256 hashed before upload and data is normalized and hashed automatically. It also notes bulk execution capability. These add meaningful context not present in the annotations, though auth requirements and failure behavior remain undisclosed.

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 relatively compact and organized with an actions list, data format, and pointers to alternatives. The create action bullet and the '[Flattened action: add_users]' note add minor noise, but overall the description is efficient and 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?

The description covers the core operation, user data format, hashing, bulk support, and delete alternative, which is helpful. However, it lacks outcome/return behavior, required parameter clarification, and guidance on account/auth selection, making it only partially complete for a 7-parameter mutation tool with no output schema.

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 defines the users array shape (email, phone?, fn?, ln?) and mentions audience_ids for batch, which is helpful. However, it does not explain other parameters such as account, auth_account, audience_id singular, name, or description, leaving significant gaps in parameter understanding.

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 clearly identifies the add_users action as uploading hashed user data, specifying PII fields and hashing behavior. It also explicitly distinguishes from the destructive delete tool, though the inclusion of a create action and the '[Flattened action: add_users]' note adds slight ambiguity.

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 description gives an explicit when-not to use this tool ('For destructive delete use meta_ads_audience_delete') and mentions bulk support via audience_ids, which signals batch usage. However, it does not contrast with meta_ads_audience_write_create or other write-oriented sibling tools, so guidance is partial.

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