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

The description goes well beyond the annotations by disclosing partial failure policy (completed_items_not_rolled_back), durable execution, billable AI usage, seatId/seatName requirements for multi-seat mutations, and a deterministic retry-key mechanism when idempotencyKey is omitted. These are concrete behavioral traits that help predict side effects. The description is consistent with the idempotentHint annotation, so no contradiction.

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 first two sentences efficiently state the primary purpose, but the remainder contains extensive generic response-handling instructions ('Use assistantSummary first...', 'Never display raw JSON...') that are not specific to this tool and are likely boilerplate. The description is lengthy and dilutes the signal-to-noise ratio, making it harder to parse the essential tool-specific details.

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?

The description covers many operational aspects: default save behavior, partial failure policy, seat authentication rules, and idempotency, which gives a fairly complete picture of the tool's runtime behavior. However, given the large parameter count (27) and 0% schema coverage, the lack of definitions for most parameters and the absence of a clear distinction from similar sibling build tools leaves significant gaps for an agent trying to invoke 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?

With 0% schema description coverage and 27 parameters, the description carries the full burden of parameter explanation. It only clarifies campaignId/campaignName, persistence, idempotencyKey, and seatId/seatName. Core parameters such as brief, assets, template, creativeIds, and instructions remain completely undefined, leaving an agent unable to correctly construct a valid call.

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?

Opens with a clear verb-object phrase 'Build and save existing Studio creative records,' immediately conveying the tool's core function and its focus on existing records. The campaign-scoped behavior and default save action add specific scope. However, it does not explicitly differentiate from sibling tools such as build_campaign_creative_set or leanriq_build_ad, which could cause confusion in an agent's tool selection.

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 gives a concrete usage scenario: supplying campaignId/campaignName triggers a full persisted inventory build, and it explicitly restricts persistence preview_only to unsaved ad-hoc previews. It also mentions mutation modes and task support. But it never names alternative tools or states when not to use this tool, leaving the when-to-use guidance implicit rather than explicit.

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