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

Annotations already cover the safety profile (readOnly=false, idempotent=true, destructive=false, openWorld=true), so the description does not need to restate them. It adds genuinely new behavior: 'Each successful file costs one credit,' which discloses a billing consequence the annotations and schema cannot express. It still omits failure/partial-success behavior when some sizes fail.

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, no filler, and the core behavior (one image per size, credit cost) is front-loaded. Tight and readable; only slightly abrupt at the end.

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 6-parameter, nested-object, credit-spending mutation with no output schema and weak schema descriptions, the description leaves major gaps: no return shape, no handling of partial failures, no explanation of data/version/template_id. It is too thin for the tool's complexity.

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 only 33% across 6 parameters (including a nested object). The description hints at the semantics of 'sizes' but adds nothing for data, version, template_id, or format beyond what the schema already encodes. It does not compensate for the coverage gap.

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 and clarifies the output shape ('one image per requested size'), which is more than the title restates. It does not, however, differentiate itself from siblings like create_ai_image, render, or create_batch, so the agent must infer which creation tool applies.

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?

The only usage-like statement is 'Reuse a key only for the same request,' which is about idempotency, not about when to pick this tool over create_ai_image or create_batch. There is no when-to-use, when-not-to-use, or prerequisite guidance.

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