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

Annotations already declare a non-read-only, non-destructive, idempotent write. The description adds meaningful side-effect context beyond that: saving spends no credits, generates no content, and does not publish, and the result is an 'inactive' draft. This reassures the agent that the write is low-risk, though it omits whether the draft can later be edited via update_* tools.

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 tight sentences with the primary action front-loaded ('Save an inactive review draft') followed by side-effect disclaimers and a scope constraint. No filler, though the final clause is slightly cryptic ('the saved automation type must match this tool').

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?

An output schema exists, so return values needn't be described, and annotations cover the safety profile. But given the deeply nested, entirely undocumented recipe object, the description is thin on how to construct a valid draft. It is adequate but leaves substantial parameter-level gaps.

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 top-level params plus a large nested 'recipe' object with many sub-fields. The description explains none of them; 'only retouched source images' loosely gestures at attachment/scoping but gives no guidance on brandId, idempotencyKey, or the recipe configuration. 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+resource: 'Save an inactive review draft.' Combined with the tool name and 'the saved automation type must match this tool', an agent can tell this creates a dormant (unactivated) retouch automation draft. It doesn't name sibling tools (e.g. activate_retouch_automation, prepare_edit_image_automation) directly, so differentiation is inferred rather than stated.

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?

'Does not generate content, spend credits or publish' implies the tool is for staging a draft without side effects, and 'the saved automation type must match this tool' constrains it to retouch. However, it never explicitly says when to reach for this versus activate_* or generate_*_sample, leaving the selection logic implied.

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