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

Annotations give readOnlyHint=false, destructiveHint=false and idempotentHint=true, so the safety profile is partially covered. The description adds real behavioral context beyond that: the saved artifact is an inactive draft, no credits are spent, nothing is published, and the automation type must match — useful for a write operation with an idempotency key.

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 and then the exclusions. Nothing is wasted, though the ordering of the type constraint could be tighter.

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 tool with a deeply nested recipe schema, zero schema descriptions and a defined output schema, the description is too thin. It covers the non-generation/inactive-draft behavior but says nothing about the recipe configuration, defaults, caps or the idempotency contract an agent must satisfy to call 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 0% across three required parameters, one of which (recipe) is a large nested object with mode enums, configuration sub-object and many bounded fields. The description explains none of this and offers no syntax, format or required-field guidance, so it fails to 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?

The description states the action (save an inactive review draft) and constrains the resource type ('Only replacement image backgrounds; the saved automation type must match this tool'), which distinguishes it from the many sibling prepare_* automation tools. It stops short of restating 'image backgrounds automation' as cleanly as the name does, but an agent can identify it.

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 implies usage by clarifying what the tool does not do (no content generation, no credit spend, no publishing) and that the automation type must match, but it never names an alternative such as activate_image_backgrounds_automation or generate_image_backgrounds_automation_sample, so routing between siblings is left to inference.

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