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

Annotations already declare destructiveHint=true and idempotentHint=true, and the description goes beyond them by specifying exactly what is destroyed (the reviewed sample is invalidated), what the tool deliberately does not do (generate or publish), and the precondition that the saved automation type must match this tool. That is the kind of side-effect and precondition detail an agent needs before mutating.

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, zero filler, with the primary effect front-loaded before the exclusions and the type precondition. Every clause carries information.

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?

Mutation semantics and sample invalidation are well covered, and the presence of an output schema excuses it from explaining return values. However, for a deeply nested 5-parameter write with 0% schema description coverage, the description leaves the concurrency control (revision) and idempotency contract unexplained.

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?

Top-level schema description coverage is 0% across 5 required parameters, and the description adds no parameter-level meaning: nothing about revision (apparent optimistic-concurrency token), idempotencyKey, or the required recipe shape. The schema's structural constraints and enums exist, but with zero textual coverage the description was expected to compensate and does not.

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?

It names a precise verb+resource ("Replace this automation's recipe") and scopes the resource type with "Only vertical story artwork," which separates it from the many update_* siblings for other artwork types. It stops short of naming a specific alternative tool, but the operation is unambiguous.

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 or publish" is an explicit when-not boundary, and "invalidate its reviewed sample" signals the downstream consequence that steers the agent toward the sample generate/approve flow afterward. No alternative tool is named directly, so it falls short of a full when/when-not routing statement.

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