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

Annotations declare write (readOnlyHint=false), idempotent and non-destructive, but the description adds genuinely useful context beyond them: this save does not generate content, spend credits, or publish. That tells the agent the operation is a cheap, non-committing write, which the annotations alone do not convey.

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, front-loaded sentences with no filler; the key effect ('does not generate, spend or publish') comes early. Appropriately tight for the behavioral message.

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 deep nested recipe schema, an output schema, and full annotations, the description covers the safety/behavioral angle well but gives the agent nothing on constructing the recipe or the idempotency contract. Adequate on conduct, thin on the actual call.

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% and there are three required parameters, including a large nested recipe object. The description explains none of them (brandId, recipe fields, idempotencyKey), so it fails to compensate for the total absence of schema documentation.

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 a specific verb and resource ('Save an inactive review draft') and clarifies it does not generate, spend credits or publish. It does not, however, distinguish itself from the activate_/resume_/update_image_generator_automation siblings, so the agent cannot tell the family members apart from this text alone.

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 the condition for use ('inactive review draft', 'only original generated images', 'the saved automation type must match this tool') but never names an alternative or says when to prefer prepare over activate/resume/update. Usage is inferable rather than stated.

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