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

Annotations only give readOnly/openWorld/idempotent/destructive hints; the description adds a wealth of tool-specific behavior: it creates billable AI usage, execution is durable, task support is optional, partial failures follow completed_items_not_rolled_back, and the idempotency key is deterministically derived if omitted. The seat-on-the-exact-call rule for writes is a concrete operational constraint the annotations do not convey.

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 is front-loaded, which is good, but the opening sentence exactly duplicates the title, and the body is a dense run-on of metadata plus generic response-style boilerplate (never display raw JSON, use assistantSummary first) not specific to this tool. Much of it earns its place, but there is real redundancy.

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?

An output schema exists so return values need no prose, and the description does note the durable run ID and honest partial states. For a complex 16-parameter, nested-schema mutation though, the near-total absence of per-parameter meaning leaves the definition incomplete for correct invocation beyond the two required/seat parameters.

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 16 parameters, so the description must carry semantics; it meaningfully explains idempotencyKey (derived retry key if omitted) and seatId/seatName (must be supplied on the write call, prior selection insufficient). But advertiserId, targetMarket(s), locale parameters, and marketContext receive no explanation at all, leaving most of the surface undocumented.

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 first sentence states a specific verb (synthesize), resource (advertiser creative opportunities) and inputs (competitor/category research + World signals), and 'creates no campaign or publication' implicitly distances it from build_campaign/build_ad. However it never names the nearest siblings (run_competitor_intelligence, run_world_intelligence, run_creative_chain, create_creative_intelligence_plan), so an agent cannot fully disambiguate from those without opening schemas.

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 exposes mutation modes (validate_only, preview_only, execute) and the seat requirement for writes, which is invocation guidance. But it never says when to choose this tool over run_creative_chain, run_competitor_intelligence, or create_creative_intelligence_plan, and there are no explicit exclusions, so usage remains implied.

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