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

The annotations already declare this is a non-read-only, open-world, non-destructive mutation. The description adds real value beyond that: cost is bounded by max_awt, dry_run returns a quote plus balance, and the call is asynchronous requiring jobs_get polling. It omits what happens when max_awt is exceeded, how idempotency_key affects retries, and any rate or failure behavior, which for an 18-parameter billable mutation is a notable gap.

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?

It is short and front-loads the cost constraint, but the telegraphic fragments ('Optional avatar.') read as cryptic rather than efficient, and the polling instruction is buried at the end. The brevity is under-specification rather than discipline.

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 six-operation, 18-parameter tool with nested objects and no output schema, three sentences is far from sufficient. Missing is any per-operation parameter mapping, the meaning of the reference roles, and what a successful response contains before jobs_get is polled.

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 0% across 18 parameters, so the description carries the full burden and largely fails. It mentions max_awt (without units or what exceeding it does), dry_run, and 'optional avatar' (without saying whether that is an asset UUID, a name, or a persona), and says nothing about references, roles, variations, wait_seconds, expand, scale, mask_asset, garment_asset, or transparent_background. An agent cannot infer which optional parameters each operation requires.

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 verb pair 'Generate/edit' plus the max_awt constraint signals a creative image operation, and the title annotation supplies the missing resource noun. But 'edit' is never decomposed into the six operations the schema enumerates (inpaint, outpaint, upscale, remove_background, try_on), so an agent must open the schema to learn what 'edit' actually covers. It also doesn't distinguish itself from creatives_list or creatives_models_list beyond implication.

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 gives two concrete procedural cues: use dry_run to quote cost and balance, and poll jobs_get for results. That is genuine when-to-do-what guidance for an async billable call. It offers no guidance on when to use this tool versus creatives_list, assets_upload_url, or references_ingest, and no per-operation conditions.

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