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

Annotations already declare write and destructive behavior, so the bar is lower. The description adds useful context beyond annotations: Pro tier requirement, live write behavior, and that audiences cost nothing until used in an ad. However, it does not explain permissions, irreversibility, or return behavior.

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 short sentences front-load the core action and append operational caveats. 'Pro.' is terse but functional, and the parenthetical about cost is efficient; there is no wasted prose.

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 purpose, plan requirement, write behavior, and filters, which is adequate for a simple create operation. But for a 5-parameter tool without an output schema, it omits what is returned (e.g., audience ID) and leaves name/meta_account_id semantics unstated.

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?

With 60% schema description coverage, the schema documents pixel_id, url_contains, and retention_days. The description reinforces retention as 'last N days' and the URL-contains filter, and mentions the account pixel. It does not clarify name or meta_account_id, and does not add default or range details beyond the 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 gives a specific verb ('Create') and resource ('a custom audience of people who visited your website'), and identifies the data source (Meta pixel). It implicitly distinguishes itself from create_lookalike_audience by defining a website-visitor audience, but does not explicitly name or contrast the sibling.

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?

There is no explicit when-to-use guidance, no when-not-to-use cases, and no named alternatives. The only contextual hints are 'Pro' and the cost caveat; an agent must infer that create_lookalike_audience is the alternative for lookalike audiences.

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