create_custom_audience

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

With no annotations, the description carries the full burden. It discloses important behaviors: errors if UET tag missing, url_contains defaults to advertiser_domain and errors if neither set, whitespace-only rejection. Still, it omits behavioral details like whether the result is a draft requiring confirmation (implied by 'Draft'), what response/identifier is returned, and any side effects of membership_duration_days. It is partial but adds meaningful value beyond the schema.

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 front-loaded with the purpose and prerequisite, then dives into url_contains behavior in a structured way. Each sentence serves a purpose, and the verification note is a minor addition. It's not overly long and avoids redundancy.

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 creation tool with 4 parameters, no output schema, and no annotations, the description is incomplete. It fails to explain membership_duration_days (though schema gives a default), what the tool returns (e.g., IDs), and whether the 'draft' nature means a separate confirmation step is needed (given the sibling confirm_and_apply). The agent might be able to call it, but important behavioral and return details are missing.

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 adds substantial meaning to url_contains: substring matching, default behavior, and whitespace rejection—exactly the kind of nuance an agent needs. But membership_duration_days is not explained at all (only its default in schema), and name/description are self-evident. The description covers one parameter in depth but leaves another interpreted while the schema provides only type and default.

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 states the tool 'Draft a remarketing list targeting site visitors,' which identifies the resource and action. It also mentions the UET tag prerequisite, adding specificity. However, it does not explicitly differentiate from sibling audience-related tools like add_audience_targeting (which applies audiences rather than creates them), so a clear distinct purpose isn't fully established.

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 provides a prerequisite (UET tag must exist, otherwise error) and explains when errors will occur, which aids the agent in deciding readiness. However, it does not mention when to use this tool versus alternatives (e.g., when creating vs. targeting audiences), so usage context is partially informative but lacks explicit alternative routing.

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