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

Beyond the sparse annotations (all false), the description discloses real behavioral traits: it consumes this month's generation allowance, requires polling a sibling job and downloading slides/zip, and forbids inventing fake UIs with a text-CTA fallback. This is exactly the kind of non-obvious context an agent needs and far exceeds what annotations provide.

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?

Three sentences with no filler. The purpose is front-loaded, followed by optional inputs/workflow, then critical behavioral constraints. Every sentence contributes essential information.

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?

Despite 8 parameters and an async job workflow, the description covers the output format, optional inputs, resource cost, retrieval method, and a key edge-case fallback. With an output schema present, no return-value details are missing.

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%, so the baseline is 3. The description adds value by mapping key optional parameters (product name, screenshot asset or URL, CTA URL) and clarifying behavior around them — specifically the fallback to a text CTA when no screenshot is provided, which is not in the schema.

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 names a specific verb and resource: 'Generate an Ad Lab Proof pack' with explicit contents (hook, niche in-the-life stills, soft CTA) and aspect ratio (4:5). This clearly differentiates it from siblings like generate_ad_studio and generate_ad_tip_pack even without seeing their 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?

The description gives useful context (generation allowance, polling get_ad_generation) and implies this tool is for creating proof packs, but it never explicitly states when to choose this over alternative generate_* tools or what conditions would route elsewhere. The guidance is inferred rather than stated.

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