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

Annotations already declare readOnlyHint=false, idempotentHint=true and destructiveHint=false, so the safety profile is partly covered. The description adds real context beyond that: no content generation, no credit spend, no publishing, and that only enhanced source images apply. This materially lowers the perceived risk of a write operation.

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 before the caveats. Nothing is padded, though the final sentence ('the saved automation type must match this tool') is cryptic enough that it costs more clarity than the space it saves.

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?

The output schema and annotations are present, so return values and idempotency need not be re-explained. However, for a tool whose schema is a deep nested recipe at 0% description coverage, the description leaves the largest source of invocation error (recipe shape and attachment roles) essentially unaddressed.

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, including a large nested 'recipe' object with dozens of properties, and the description explains none of them. It gestures only obliquely at attachment roles ('only enhanced source images') and the type constraint, adding almost no usable parameter guidance.

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: 'Save an inactive review draft.' Combined with the tool name and the 'automation type must match this tool' constraint, an agent can tell this persists a draft rather than activating or running anything. It does not explicitly contrast with siblings like create_draft or update_image_enhancer_automation, so sibling differentiation rests mainly on the name.

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 description gives useful negatives ('Does not generate content, spend credits or publish') and a matching constraint, which implicitly frames this as the safe, pre-activation save step. But it never states when to use prepare_* versus activate_*, update_*, or resume_* siblings, leaving the alternative selection to inference.

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