audience_recommendations

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

The annotations declare readOnlyHint=true, so behavior is read-only. The description adds context about the output categories (in-market, affinity, demographics, bid modifiers) but does not disclose any additional behavioral traits such as rate limits, authentication requirements, or whether external AI calls occur. No contradiction with annotations, but limited extra transparency.

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 concise and front-loaded with the core purpose. The second sentence elaborates on outputs, and the 'Args' block is a compact, scannable list of parameters. Every sentence adds value, and there is no redundancy or fluff.

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?

No output schema exists, so the description must cover return structure; it lists the categories returned but not the format (e.g., score/confidence values, structure). The undocumented 'config' parameter is a gap. For a tool of this complexity, the description is mostly sufficient but not fully complete.

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?

Despite 0% schema description coverage, the description explains three of four parameters (keywords, campaign_type, industry) with examples and defaults. It clarifies allowed values for campaign_type and typical industries. However, the 'config' parameter is completely absent from the description, leaving its purpose unexplained.

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's purpose: 'Get AI-recommended audience signals for a Google Ads campaign.' It specifies the resource (audience signals) and action (get/recommends), and lists concrete output types (in-market segments, affinity audiences, demographics, bid modifiers). This distinguishes it from sibling tools like audience_segments or demographic_options by emphasizing AI-driven, keyword-based recommendations.

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 clear usage context: it is used when you want audience recommendations based on keywords and industry. However, it does not explicitly contrast with alternative tools or state when not to use it. The examples and default values give practical guidance, but there is no explicit exclusions or comparison to siblings.

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