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

Annotations already cover the safety profile (non-read-only, open-world, non-idempotent, non-destructive). The description adds information the annotations cannot: the plan/billing gate, the model fallback behavior when Google fails (relevant to output consistency), the 'no faces' content constraint, and the return value. That is substantive disclosure beyond structured fields.

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?

Two sentences, front-loaded with the capability and constraints, no filler. Dense parentheticals ('GPT Image 2.5 if Google fails') trade a little readability for efficiency, but every clause carries 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?

There is no output schema, and the description compensates by stating the return value ('Returns the image URL'). Combined with plan gating, model fallback, aspect-ratio constraint and reference limits, an agent has everything needed to call this correctly for a 3-parameter, single-required-parameter tool.

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 baseline is 3. The description still adds workflow meaning by connecting style_references to list_viral_youtube_videos and clarifying that only layout and colours are borrowed (not content), which goes slightly beyond the schema's wording.

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 ('Create a ... 16:9 YouTube thumbnail'), plus differentiators that separate it from generate_image/edit_image: no faces, fixed 16:9, Gemini 3 Pro Image with a GPT Image 2.5 fallback. An agent knows exactly what this produces and that it is a thumbnail-specific generator, not a general image tool.

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?

Gives a hard prerequisite ('Paid plans only') and routes the agent to a sibling ('e.g. from list_viral_youtube_videos') for sourcing style references. It does not explicitly say when to prefer this over generate_image, but the niche-specific scope and paid-plan gate give clear selection context.

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