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

No annotations are provided, so the description carries full burden. It discloses that signals are deterministic, real-time, captured by on-device cameras/microphones, and analyzed via ML Kit and Gemini Vision. It also states what the tool returns. It does not explicitly state that this is a read-only operation, but the verb 'get' and the return-focused description make the read-only nature clear.

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 well-structured with clear sections: a one-line summary, context, WHEN TO USE, returns, and examples. It is longer than average but every section adds useful information, and the critical summary is front-loaded. The two example forms are especially valuable and not redundant.

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?

Given there is no output schema, the description compensates by enumerating the return shape: signals array with demographics, venue, behavior, geo, plus metadata with screen counts. The optional and nested signal_spec is fully explained with examples, and pagination is the only uncovered parameter, which is minor. For a read-oriented signal query tool, this is complete enough for an agent to call it correctly.

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 only 50%, so the description must compensate, especially for signal_spec. It does so thoroughly by explaining both the AdCP natural-language form and the structured form, and by providing two concrete examples. The pagination parameter is not mentioned, but its schema is self-explanatory and the description's focus on signal_spec is where the real ambiguity lies.

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 opens with a clear verb-resource pair: 'Get real-time audience signals from DOOH screens,' and elaborates that signals are deterministic audience data captured by edge AI. It does not explicitly differentiate from sibling tools like get_live_audience or get_attention_metrics, but the AdCP framing and deterministic-data emphasis give it a distinct identity.

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 WHEN TO USE section lists three concrete business scenarios: discovering signals before buying, evaluating venue audience composition, and building targeting segments. It also contrasts against probabilistic data, which helps an agent choose this over probabilistic alternatives. It does not name specific sibling tools or exclusion conditions, so it stops short of full routing guidance.

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