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

Annotations only declare the generic write/openWorld/non-destructive profile; the description adds genuinely new behavior: SHA-256 hashing is applied before transmission, raw data is never persisted, and there is a hard 10,000-row ceiling per call with an append path via audience_id. What it omits is the outcome of the call (does it return a new audience ID?) and whether the created audience is immediately usable.

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 with no filler: the core action and data-handling guarantee come first, then the operational constraints (phone format, row limit, append behavior). Every clause carries information an agent needs before invoking the tool.

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 7-parameter write tool with no output schema and no required fields, the description covers the data-handling contract, size limits, and the incremental-add pattern, which are the highest-risk unknowns. The remaining gap is silent on the return value and on the implicit account/folder targeting that an agent must otherwise infer from the 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 coverage is 57%, and the description compensates for the undocumented array parameters by specifying the hashing applied to emails/phones, the required country-code format for phones, and the per-call row cap plus the audience_id append semantics. It adds nothing about name, folder, account, or language, which remain schema-only, so it is above baseline but not exhaustive.

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 uses a specific verb and resource ('Create a custom audience from customer emails and/or phone numbers'), and the 'customer list' qualifier distinguishes it from the generic meta_create_audience and the read-only meta_audiences/meta_saved_audiences siblings. It stops short of explicitly naming which sibling to use for non-customer-list audiences, so it is clear but not fully differentiated.

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?

Usage context is strongly implied (you have a customer list of emails/phones to upload) and the description gives a concrete workflow rule: call again with audience_id to add beyond 10,000 rows. However, it never states when NOT to use this versus meta_create_audience or meta_audiences, nor any prerequisites such as which account or folder to target.

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