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

Annotations already declare idempotentHint=true, destructiveHint=true, and readOnlyHint=false. The description adds real value by disclosing that the recipe is replaced and the reviewed sample becomes invalid, and that nothing is generated or published. However it omits consequences of the destructive replace (e.g., in-flight runs, loss of prior recipe) and permission requirements.

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, reasonably front-loaded with the core action, but the final sentence ('Only edited source images; the saved automation type must match this tool') is grammatically compressed and ambiguous, weakening clarity rather than earning its brevity.

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?

Given a destructive, idempotent mutation with a complex nested recipe schema, the description covers the high-level intent and the sample-invalidation effect, and an output schema exists so return values need not be explained. It is still thin on the revision/precondition semantics and on what 'edited source images' means in practice.

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%, but the schema is extremely rich with nested constraints, enums and defaults, so the baseline is 3. The description references 'recipe' at least conceptually but adds no semantics for brandId, automationId, revision (optimistic concurrency), or idempotencyKey, leaving the agent to infer revision and idempotency handling from names alone.

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?

Clear specific verb+resource: replaces an automation's recipe and invalidates its reviewed sample. Distinguishes from sibling update_* tools by stating it only works on 'edited source images', but this constraint is cryptic and not framed in terms an agent can readily compare with siblings like update_image_enhancer_automation.

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?

States a key precondition (the saved automation type must match) and notes it does not generate or publish, which implicitly distinguishes it from generate_edit_image_automation_sample and the activate_* tools. But it never names an alternative or gives explicit when-to-use guidance against the many sibling update_* tools.

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