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

The annotations already declare readOnlyHint, idempotentHint, openWorldHint and destructiveHint=false, so the safety profile is fully covered by structured data. The description adds one piece of context beyond that: the returned audience IDs are meant for adset targeting/exclusion settings, which helps an agent wire the output into a follow-up call. It says nothing about result size, pagination, or whether lookalike and custom audiences differ in shape.

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 definition is short, but the second sentence largely restates the first, re-listing 'custom and lookalike audiences of an ad account' before adding the new detail about targeting fields. Merging the two would preserve all information in a single front-loaded sentence.

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 simple two-parameter read-only list tool with rich annotations and no output schema, this covers the essentials of what it returns and why. The gaps that matter are the unexplained search filter and the absence of any note on pagination or result volume.

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 only 50%: ad_account_id has a description and pattern, but the 'search' parameter has no schema description at all. The description never mentions free-text search or name filtering, so the one undocumented parameter is left entirely unexplained to the agent.

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 identifies a specific resource (Meta custom and lookalike audiences) scoped to an ad account and states the intent (to target or exclude). It is a noun phrase rather than a verb, but the list semantics are unambiguous, and the downstream field references (adset_settings.custom_audience_ids / excluded_audience_ids) confirm what the tool produces. It does not explicitly distinguish itself from the nearby list_targeting / search_targeting siblings.

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 is only implied: the description explains that the results feed targeting or exclusion fields on adsets, which tells an agent where the output belongs. It never states when to call this instead of list_targeting or search_targeting, nor any prerequisites such as which account or permission is needed.

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