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

With no annotations, the description carries behavioral weight and reveals non-obvious behavior: activation keys expire in 24 hours, IAB segments are emitted only when registered IDs are supplied explicitly, and free-form labels remain custom parameters. It also lists return fields. It does not disclose idempotence, overwrite semantics, or permission requirements, but it provides substantial behavior 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 organized into front-loaded purpose, WHEN TO USE, RETURNS, and EXAMPLE sections with no filler. Every section carries operational information, and the structure lets an agent scan it quickly.

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 no output schema and no annotations, the RETURNS list and example materially help the agent understand the call's outcome and shape. The main gaps are that signal_type's other values (venue, behavior) and the destinations parameter are not addressed, so less canonical calls would rely on schema-only inference.

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 80%, so the baseline is 3. The description adds a concrete example mapping a natural-language income segment to iab_audience_segment_ids: ['68'], plus the rule that inferred labels are never auto-mapped. It also clarifies the role of screen_ids through the example, though destinations and other signal_type values are not discussed.

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 'Activate an audience signal for DSP targeting,' identifying a specific verb, resource, and use context. It further differentiates from siblings like get_signals and semantic_audience_search by stating it returns an activation_key token for referencing the activation.

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?

A dedicated WHEN TO USE section lists three concrete invocation contexts, including converting audience signals into targeting parameters and activating registered IAB segment IDs. It does not mention when not to use this tool or name alternative sibling tools, so it stops short of the strongest exclusion guidance.

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