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

Annotations already declare destructiveHint=true, openWorldHint=true and non-idempotent, and the description corroborates them with 'Edits can overwrite content' and the clarification that this is not an arbitrary external-tool dispatcher (consistent with openWorldHint). It adds real context beyond annotations — recipe-based compound repairs and the instruction to preserve the user's exact wording and target element/print area — though it does not describe the response or failure behavior.

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-loaded with the core action, then scope boundaries and exclusions — a sensible order. The capability enumeration partly duplicates the sibling tool names and is the densest part, but it earns its place by telling the agent which intents this dispatcher absorbs.

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?

For a broad, high-parameter dispatcher with nested objects and no output schema, the description supplies the essential framing: what it covers, that it mutates and can overwrite, that operation selects a recipe, and which tools to use instead. The remaining gap is return/verification behavior, which matters given destructiveHint=true and the availability of preview_design and validate_design.

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 description coverage is 100%, so baseline is 3, but the description adds meaning the schema lacks: 'operation selects a design recipe, including compound image/text repairs' explains the otherwise undocumented `operation` field, and 'Preserve the user's exact instruction and intended element/print area' guides how to fill the free-form instruction and element/area targeting. The many advanced/alias fields remain unexplained, so it stops short of 5.

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 ('Apply the existing natural-language edit to the current design') and enumerates the capability domains it covers (text, image replacement, sizing, positioning, background removal, crop/flip, contrast, keyline, emoji). It explicitly distinguishes itself from the individually named sibling tools and from upload/generation/photoshoot/email/checkout tools, so an agent can place it in the toolset without opening the schema.

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?

Explicit exclusions are given ('Use the separate upload, artwork-generation, photoshoot, email and checkout tools for those actions') and the tool is scoped away from being a generic dispatcher. However, it says the covered capabilities 'also have individually named tools in this list' without saying when to prefer change_design over add_text/update_text/crop_image etc., leaving the primary routing ambiguity unresolved.

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