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

With no annotations provided, the description carries the full burden of behavioral disclosure, and it does so meaningfully: it states that prompts and results are checked against a content policy, refused outputs are not charged, and the return format is base64 PNG. It omits other potential behaviors like latency, rate limits, or image permanence, but the key operational expectations (safety screening and billing) are disclosed.

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 with zero filler: the first delivers the core action and output format, the second discloses policy and billing implications. Every sentence earns its place, and the most decision-relevant information is front-loaded.

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?

The tool is simple (two params, one required, full schema coverage), and the description covers the essential runtime behavior: output format, content policy, and charge exemption on refusal. Since there is no output schema, the description properly explains what callers receive. It could go further by mentioning size's default or prompt guidance, but the schema already handles those, leaving no critical gaps for an agent to invoke it correctly.

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 input schema fully documents both parameters including descriptions and an enum for size. The description adds no extra parameter-level detail beyond the schema—confirming that 'prompt' is textual but not elaborating on how to craft effective prompts or how 'size' maps to orientation. Baseline 3 is appropriate because the schema carries the semantic load.

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 states a specific verb ('Generate'), a clear resource ('an original image'), and the output format ('base64 PNG'), which fully communicates what the tool does. With no sibling tools, differentiation is unnecessary, but the action–resource–format triad makes the purpose unambiguous.

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?

There are no sibling tools or alternatives to contrast, so the description instead establishes context by specifying the input (text prompt) and output (base64 PNG). It also hints at usage expectations around content policy refusals, though it doesn't explicitly say 'use this when you need an image'—that is clear enough from the purpose statement.

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