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

Annotations already declare destructiveHint=true, idempotentHint=false and non-read-only, so the safety profile is covered. The description adds real value beyond that: 'Send only what changes' (patch semantics), that it returns preview images and warnings, and that the open_url from create_design then opens the new version.

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?

Front-loads the core action and scope in the first clause and wastes no sentences, but the trailing sentence about edit_asset and saved designs is dense and somewhat tangled. It mostly earns its place, though it could be split for clarity.

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?

With no output schema, the description correctly fills that gap by stating what is returned (preview images and warnings) and how the returned open_url behaves. Combined with sibling routing, an agent has enough to call it, though the edit_asset/saved-design relationship remains slightly ambiguous.

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 already documents both top-level parameters and every nested op field, including the meaning of design_handle. The description's 'send only what changes' reinforces partial-update semantics but adds little syntax or meaning beyond what the schema provides, making 3 the correct baseline.

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?

States a specific verb and resource ('Changes a design create_design made') and enumerates the exact scope of operations (layer field edits, add/remove/reorder, variant background/loop/title replacement, add/remove variant). It explicitly ties itself to create_design, distinguishing it from siblings that also mutate designs.

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?

Sets the operative condition 'before the user saves it' and routes the agent to alternatives ('one the user already saved changes in the editor (or with edit_asset)'). The edit_asset vs editor guidance is present but expressed indirectly rather than as a crisp when-not rule.

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