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

"Bounded allowance" discloses a quota/cost constraint and "can return pending work" discloses async/polling behavior — both are useful beyond the annotations. However, destructiveHint=true is never explained: the description doesn't say generation can overwrite existing design content, which is the single most important behavioral fact for an agent calling this.

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?

Three short sentences, front-loaded with the core action, then usage hints, then behavioral caveats. No filler, though the middle sentence's phrasing slightly buries the parameter hint.

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?

No output schema exists, so the description should at least sketch what comes back (asset, pending status), and it only gestures at pending work. The destructive side effect and the cost of burning allowance on a bad prompt are left implicit, which is a real gap for a mutation tool.

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 schema already documents requestId polling semantics and sessionToken. The description adds workflow meaning by grouping applyToDesign, singleResult and areaId as the "apply to shirt" combination, but contributes nothing about subject, sessionToken, or prompt.

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 first sentence gives a specific verb+resource ("Generate artwork from a prompt") plus the backing service, so an agent knows this is a text-to-image generation call. It doesn't distinguish itself from adjacent siblings like ai_photoshoot, extract_artwork, or upload_image, so it falls short of a 5.

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?

"Use applyToDesign, singleResult and areaId when applying it to a shirt" gives some situational guidance, but there is no when-not guidance and no named alternative for plain image insertion or photoshoot-style generation. Usage is implied rather than framed as a decision rule.

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