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

Annotations already declare this is a non-idempotent write (readOnlyHint=false, idempotentHint=false). The description adds meaningful context beyond that: 'confirm=false → dry-run' tells the agent that creation will not execute without explicit confirmation, which is an important behavioral safeguard not captured by the annotations.

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?

Four compact sentences/segments with no filler, and the core purpose is front-loaded before the format and workflow details. Efficient for a 7-parameter 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?

An output schema exists, so return values need not be explained. The description covers creation, seed prerequisites, format conventions, expansion options, and the dry-run safety behavior; it is nearly complete for an agent to invoke correctly, with only minor gaps like membership_days semantics.

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 0% schema description coverage, the description carries the full burden and does well for the tricky parameters: it specifies comma-separated list formats with examples for seed_user_list_ids and country_codes, and enumerates expansion_level values (NARROW | BALANCED | BROAD), which the schema lacks as an enum. customer_id, name, and membership_days remain undocumented, but the critical format ambiguities are resolved.

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?

States a specific verb and resource ('Creates a Lookalike audience from seed audiences'). However, it does not distinguish itself from platform-specific siblings like create_meta_lookalike_audience or create_tiktok_lookalike_audience, leaving ambiguity about which of the three tools to choose.

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?

'Run list_audiences first for valid seed ids' provides a useful workflow prerequisite, but there is no explicit guidance on when to use this tool versus the platform-specific lookalike tools, nor any stated exclusion conditions.

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