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

Annotations declare readOnlyHint=false, destructiveHint=false and openWorldHint=true, but the description adds genuinely new behavioral context: the billing model (charged only for returned layers, failed splits fully refunded) and the concrete output shape (base + up to 16 named, placed transparent PNGs). It does not, however, disclose latency or async/job-status behavior for a generation task.

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?

Two sentences, front-loaded with the core action and quantified output, then input guidance and pricing. No filler and every clause carries information.

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 steps in to describe the return (base plus up to 16 named, placed transparent layers) and the cost/refund behavior. Combined with 100% parameter coverage, an agent has everything needed to invoke 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?

Schema description coverage is 100%, so the baseline is 3. The description reiterates asset_id, the “my last image” alias, the optional instruction, and size, but adds no syntax or format detail beyond what the schema already documents.

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 (“separate ... images into editable layers”) and quantifies the output (a base plus up to 16 transparent PNG layers). The named model (Seedream 5.0 Pro) and output structure make the purpose unambiguous, though it never names an alternative such as flip-side sibling flatten_layer_set to differentiate route.

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?

It scopes the tool to “one of your own Switch images” and tells the caller how to specify the input (asset_id or “my last image”), which is useful. However it gives no when-to-use vs alternatives guidance and no exclusions, leaving usage only implied.

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