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

Annotations already declare destructiveHint=true and idempotentHint=true, so the safety profile is covered. The description adds real behavioral context beyond that: the recipe is replaced (not merged), the reviewed sample is invalidated, and no generation or publishing occurs. This is valuable, though it omits permission/auth requirements and whether the invalidation is reversible.

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, front-loaded with the core action and its side effect. Every clause carries information. Minor deduction because the trailing type-matching constraint is a bit cryptic without elaboration.

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 complex mutation tool with nested objects, the description covers the critical behavioral facts (replace, invalidate, no generate/publish, type match), and an output schema exists so return values need no explanation. What is missing is parameter-level guidance, which matters given 0% schema coverage.

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%, so the description must compensate for five required parameters (brandId, automationId, revision, idempotencyKey, recipe) and a deeply nested recipe object. The description explains none of them — not what 'revision' means, not why 'idempotencyKey' is required, not the recipe fields. The schema's structural detail partially offsets this, but the parameter semantics burden is unmet.

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 names a specific verb (Replace) and resource (this automation's recipe) plus a secondary effect (invalidate its reviewed sample). The clause 'the saved automation type must match this tool' distinguishes it from the other update_*_automation siblings. It stops short of naming an alternative explicitly, so it is clear but not fully sibling-differentiated.

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 gives useful scope constraints ('Does not generate or publish', 'Only enhanced product images', type must match), which tell the agent what this tool is not for. However, it never routes the agent to the alternative tools (generate_*_sample, prepare_*, activate_*) that handle those excluded actions. Usage is implied rather than explicitly directed.

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