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

Annotations only declare the safety profile (non-read-only, non-idempotent); the description goes beyond them by disclosing that generation runs in the background, that it consumes an AI generation turn, and that it does not draw an Ad Run credit. These are non-obvious operational and quota behaviors an agent would otherwise have to guess.

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?

Front-loads purpose in the first sentence, then uses compact Args/Returns/workflow blocks. Every sentence is actionable and none is 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?

With no output schema, the description supplies the return shape (job id/status/prompt/variantCount/results, note) and the full next-step sequence, so an agent can call this correctly and act on the result without further 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 description coverage is 0%, so the description carries the burden; it documents ideaId and explains that prompt is optional with a concrete default (the idea's saved image prompt). The third parameter, response_format (enum), is left undocumented in both places, so it does not fully compensate.

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?

States a specific verb+resource ('Start generating hero image variants for an idea's ad') with the scope of the operation (image variants for an ad). It is clearly distinguishable from siblings like idealaunch_get_image_job (polling) and idealaunch_apply_hero_image (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?

Explicitly sequences the workflow: start here, poll idealaunch_get_image_job until status 'succeeded', then apply with idealaunch_apply_hero_image. It also frames the cost model ('consumes one AI generation turn', 'costs no Ad Run credit'), giving the agent everything needed to decide when to call this.

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