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

Annotations already indicate destructiveHint=true and readOnlyHint=false. The description adds useful context: it clarifies the edit is instruction-based, only affects the background layer, and returns the edited URL. It also mentions 'the editor swaps the background layer', which explains the mutation behavior. This goes beyond the annotations without contradicting them.

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 compact and well-structured: a core purpose sentence, a scoping note, a 'USE FOR' line with examples, and an 'OUTPUT' line. Each sentence earns its place, and the most important info (purpose and scope) is front-loaded. No wasted words.

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 complexity (3 params, no output schema, AI edit), the description covers the core behavior, gives usage examples, and states the output format. It also differentiates from a sibling. A minor gap is that it doesn't explicitly state whether the original creative is updated or if only the URL is returned, but the 'editor swaps the background layer' hints at it. Overall, it's sufficient for an agent to call 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?

The input schema has 100% coverage, providing descriptions for all three parameters (domain, image_source, edit_instruction). The tool description adds some value by giving example instructions in the 'USE FOR' section and clarifying that the edit is free-text, but it doesn't add meaning beyond what the schema already states for domain or image_source. 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 states a specific verb ('apply'), resource ('flexible creative's BACKGROUND image'), and outcome ('return the edited image URL'). It explicitly differentiates from the sibling edit_brand_creative by scoping to the background and mentioning that text/logo layers are never touched. This gives a clear, unambiguous purpose.

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 'USE FOR' section provides concrete example instructions, and the scoping note ('scoped to the background so the crisp editable text/logo layers are never touched') implies when to use this over edit_brand_creative. However, it doesn't explicitly state 'use edit_brand_creative for whole-image edits' or list any other exclusions, so it's slightly below a perfect score.

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