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

Annotations cover safety (readOnly=false, destructive=false, idempotent=true), and the description goes well beyond them: billable AI usage classification, durable execution, completed_items_not_rolled_back partial-failure behavior, deterministic idempotency-key derivation on omission, and the 'must supply seatId/seatName on this exact call' write constraint. This is the substantive context an agent needs before a paid mutation.

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 purpose sentence is front-loaded and earns its place, but the description duplicates the title verbatim (including a stray '..'), then pads with generic response-style boilerplate about never showing raw JSON and assistantSummary that is not tool-specific. Roughly half the text is reusable cross-tool guidance rather than this tool's semantics.

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?

With an output schema present, return values need no explanation, and the description still covers mutation modes, failure policy, idempotency, and seat auth. The main gap is guidance on the many nested creative/dooh parameters, though the schema's typing and enums carry much of that load.

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 0% across 18 parameters, so the description has to compensate; it does so for only two (idempotencyKey derivation and seatId/seatName write requirement). The rich nested objects (copy, assets, format, doohContext) are left entirely to the schema structure, so the compensation is partial.

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 names a specific verb and resource set: DOOH-native two-concept build, comparison of Studio-rendered posters, and return of an editable non-interactive CreativeDocument. It explicitly distinguishes itself from the Display path ('does not route through Display build_ad'), so an agent can separate it from the many build_* 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?

It tells the agent what this is not (build_ad), lists the mutation modes (validate_only, preview_only, execute) that drive how to call it, and states the seat requirement for writes. It stops short of naming when to prefer leanriq_build_dooh or build_videoad, so alternative routing is only partially resolved.

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