auto_adjust

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

With no annotations provided, the description carries the burden of explaining behavior. It discloses that the tool modifies whiteBalance/tone/vibrance, preserves existing detail and geometry settings, and returns the new recipe rather than saving it directly. This is useful and non-obvious behavior, though it does not mention potential side effects like overwriting previous values or needing permissions.

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 concise sentences that pack in the core behavior, what is preserved, the return value, and a follow-up instruction. No wasted words, and key information is front-loaded with the tool's purpose.

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 no output schema and no annotations, the description covers the essential aspects: what the tool does, what it changes, what it preserves, what it returns, and how to use the result. It does not explain failure modes or parameter details, but for a recipe-adjustment tool this is reasonably complete for an agent to use 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 descriptions are completely absent for the two parameters, so the description must compensate. It indirectly explains image_id by saying 'analyzes the image' and links white_balance to 'gray-world WB', but it does not explicitly state what the boolean white_balance parameter does (e.g., whether false disables white balance adjustment). The parameter meanings are inferable but not directly spelled out.

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 identifies the tool as a computational auto-adjust that analyzes an image and sets white balance, tone, and vibrance. This distinguishes it from sibling tools like update_recipe or set_recipe, which are manual recipe adjustments, by emphasizing the automatic, analysis-driven nature.

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 an explicit workflow hint: 'render_preview afterwards to judge the result.' This tells the agent when to use it relative to the sibling tool render_preview. It does not explicitly rule out alternatives, but the context suggests it is for automatic adjustments rather than manual recipe editing.

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