photoshop_recipe_remove_distraction

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. It covers the fallback mechanism (generative vs content-aware), the undoable step, the side effects (fills/removes selected pixels; clears selection), the return structure ({ ok, summary, undo_history_states_consumed, details }), and preconditions. This is comprehensive and transparent about what the tool does and its consequences.

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 well-structured with clear sections: a core summary, example user phrasings, explicit use/when-not guidance, return format, preconditions, and side effects. It front-loads the primary function and organizes supporting details logically. Every sentence adds value, and there is no fluff or redundancy, making it efficient for an agent to parse.

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 lacking an output schema, the description explicitly lists the return object's fields. It covers preconditions, side effects, fallback behavior, and usage conditions. For a tool with three optional parameters and no complex nested objects, this is fully sufficient for an agent to invoke it correctly. The only missing element might be error cases, but the description is otherwise 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?

The input schema already provides descriptions for all three parameters (feather_px, document_id, use_generative), so schema coverage is 100%. The description does not add significant meaning beyond the schema—it mentions 'generative AI remove when available' which relates to use_generative, but the schema already explains that parameter. Since the schema carries the heavy lifting, the baseline of 3 is appropriate.

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 opens with a precise statement of what the tool does: 'One-shot distraction removal: generative AI remove when available, else content-aware fill.' It names the specific operation (removing distractions) and the mechanism, clearly distinguishing it from sibling tools like photoshop_generative_remove and photoshop_content_aware_fill, which are lower-level operations. The phrase 'one-shot' and 'wrapped in a single undoable history step' further differentiates it as a recipe 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?

The description gives explicit use conditions: 'Use when: the user has selected the object or region to remove' and 'Do NOT use when: no selection exists — use photoshop_select_rectangle or photoshop_select_subject first.' This provides clear when-to-use and when-not-to-use guidance, naming the specific alternative tools to use instead. It also states preconditions (active document with active pixel selection), making the call conditions unambiguous.

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