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

Annotations only declare the mutation/safety profile (readOnlyHint=false, destructiveHint=false, idempotentHint=false, openWorldHint=false); the description adds genuinely new behavior: asynchronous background execution, the 'succeeded' status gate for results, consumption of one AI generation turn, and zero Ad Run credit cost. These are exactly the side-effect details an agent needs before invoking. It stops short of 5 because error/failure behavior and any auth prerequisites are not mentioned.

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-loaded with the action and the background-execution fact, then structured into Args and Returns. The Args block partially restates the schema, but it earns its place by adding the prompt default. Slightly list-heavy but no filler sentences.

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?

There is no output schema, and the description compensates by sketching the return shape ({ job: { id, status, prompt, variantCount, results }, note }) and the completion condition. For an async mutation tool this covers what an agent needs to call and poll correctly; the undocumented response_format parameter and absent failure modes are the remaining holes.

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, and it does document ideaId and prompt with a useful default ('defaults to the idea's saved image prompt') that the schema does not express. However, the third parameter, response_format (enum markdown/json), is documented nowhere, leaving a real gap. Partial compensation warrants a 3.

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 and resource ('Start generating hero image variants for an idea's ad') plus the execution mode ('Runs in the background'), which is enough to distinguish it from read-style siblings like idealaunch_get_image_job. It does not explicitly name or contrast a sibling such as idealaunch_generate_ad_assets, so it falls short of a 5.

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?

Usage is only implied: the agent can infer this is the tool that kicks off hero image generation, and it learns that variants become available once status is 'succeeded', which hints at following up with a job-status tool. There is no explicit when-to-use vs. when-not-to-use guidance or named alternative for other image/ad asset generation.

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