Plan ad variations

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

The description accurately states the tool renders nothing itself and is limited to LLM planning, aligning with annotations (no destructive or read-only behavior). It adds context that the tool creates multiple ad angle plans, which is beyond the annotations.

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 description is extremely concise: two sentences, no wasted words. Front-loaded with the core action 'Fan a brief into N distinct ad angles', then explains the follow-up steps and boundary.

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?

Given the tool's complexity (generating multiple ad variants with downstream steps) and the presence of an output schema, the description fully covers what the tool does and its role in the pipeline. It tells the agent what to expect and what actions to take next.

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 coverage is 100% with descriptions for all parameters. The description adds value beyond the schema by explaining the brand parameter's default behavior ('OMIT to use the workspace’s saved brand') and the count default (6).

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 clearly states the tool's function: fanning a brief into distinct ad angles with headlines and visual briefs, then delegating rendering and ranking. It distinguishes itself from siblings by emphasizing it's planning-only and renders nothing itself.

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 explicitly notes the tool is planning-only and implies follow-up with generate_image and score_ad. It provides clear context for use but lacks explicit when-not-to-use guidance or direct comparison with the sibling plan_ad.

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