photoshop_recipe_dodge_burn

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

Although there are no annotations to rely on, the description goes beyond the basic action by disclosing side effects (adds one 'Dodge & Burn' layer above the active layer), the undoable nature (single history step, one undo reverts), and preconditions (active document with raster-compatible layer). It also details return values explicitly, which is valuable. The only minor gap is that it doesn't specify error behavior if preconditions are not met, but the provided information is already strong for a tool with no annotations.

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 tightly organized, with the core purpose in the first sentence, followed by user phrasing, clear usage conditions, returns, and side effects in a logical flow. Every sentence adds critical information without redundancy. It avoids unnecessary fluff and is appropriately front-loaded with the most important details.

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 the tool's moderate complexity (one layer creation with two modes), the description covers all essential aspects: purpose, usage scope, return format, preconditions, side effects, and alternatives. It also compensates for the lack of output schema by explicitly listing the return structure. An agent can confidently select and invoke this tool correctly based on the description alone.

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 describes both parameters with 100% coverage: blend_mode is an enum with default and the document_id has a clear description. The description adds contextual value by clarifying that blend_mode's 'overlay' is stronger and 'soft_light' is gentler, and it explains why document_id is useful (prevents UI tab switch retargeting). This goes beyond the schema, earning a score above the baseline of 3.

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 verb (creates) and the resource (a dodge & burn setup layer), and it specifies the exact technical setup: 50% gray layer in Overlay or Soft Light mode. It explicitly distinguishes itself from the sibling photoshop_recipe_enhance_portrait by noting it is for manual painting, not automated smoothing. This high specificity leaves no ambiguity about what the tool does.

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 provides explicit 'Use when' and 'Do NOT use when' conditions. It names the alternative tool (photoshop_recipe_enhance_portrait) for automated smoothing, and clarifies that this tool is for manual retouching only. This gives the agent clear routing guidance with minimal inference needed.

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