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

Annotations already establish read-only and idempotent behavior. The description adds that the tool returns a styled prompt stack rather than a direct image, and that it should be followed by generate_image, providing useful behavioral context beyond safety hints.

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 two sentences, front-loaded with the core purpose, followed by options and output guidance. Every word contributes, with no redundancy or fluff.

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?

For a simple read-only tool with no output schema, the description covers purpose, output (prompt stack), usage context (pair with generate_image), and parameter choices. Annotations cover side-effect safety, making this sufficiently complete.

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 mentions 'Choose grade: warm golden, cool noir, or moody desaturated' but does not add information beyond the schema's detailed enum descriptions. The 'for your shot' phrase weakly hints at the subject parameter, but adds little value.

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 applies an ARRI Alexa anamorphic widescreen film look, giving a specific verb and resource. It differentiates from sibling apply_* tools by naming the exact cinematic style and available grades.

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 says 'pair it with generate_image', indicating when to use the tool as a preparatory step for image generation. It does not mention alternatives or exclusions, but the style-specific context is clear enough to guide selection.

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