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

Annotations already indicate readOnlyHint=false (mutating), but the description adds critical context: the tool does NOT edit in place, preserving the original and library creatives, and outputs a temporary URL. This is valuable behavioral detail beyond annotations, though it doesn't cover all edge cases like rate limits or auth, but for this category it's strong.

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 (USE FOR, EDITABLE, EXAMPLES, PRESERVES, CHAINED EDITS, OUTPUT), each sentence earning its place. It's front-loaded with the purpose and then provides actionable details. No filler or redundancy.

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 (AI editing, chained operations, brand consistency), the description covers all essential aspects: what it does, what can be edited, what is preserved, how chaining works, and the output behavior. It also clarifies the relationship with upload_image_creative, ensuring the agent knows how to persist edits.

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 schema describes all three parameters. The description adds semantic nuance by clarifying that image_source can be a URL from a previous generation/edit and that edit_instruction can include multiple changes in one request, but it doesn't add much beyond what the schema already states. Baseline 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 clearly states that the tool creates an edited copy of an existing creative image using AI editing, with explicit details on what can be edited (headlines, CTA, hero graphics, etc.). It distinguishes from siblings like generate_brand_creative and upload_image_creative by emphasizing editing existing images and preserving brand consistency.

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 FOR' guidance and examples, clearly indicating when to use this tool (e.g., for modifying existing creatives) and implicitly when not to (e.g., for creating new ones, which would use generate_brand_creative). It also mentions chained edits and the need to upload results for permanent storage, guiding the agent on post-edit workflow.

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