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 the concrete destruction detail — that the reviewed sample is invalidated — and clarifies that no generation or publishing occurs, which is real context beyond the flags. It does not discuss permissions or whether the replacement 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 short sentences, front-loaded with the primary mutation and its invalidation effect, with the constraint and scope appended. Efficient, though 'Only replacement image backgrounds' is slightly clipped phrasing.

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 need not be described, and annotations cover the destructive/idempotent profile. Still, for a 5-param nested-object mutation with 0% schema description coverage, the definition omits how revision and idempotencyKey interact with concurrency and retries — a meaningful gap for correct invocation.

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 5 required parameters, including a deeply nested recipe object, so the description must carry the load. It only gestures at 'recipe' and the automation-type precondition; brandId, revision (optimistic concurrency), and idempotencyKey are left entirely unexplained despite being central to a destructive, idempotent mutation.

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 states a specific verb+resource ('Replace this automation's recipe') plus a distinct side effect ('invalidate its reviewed sample'), and scopes itself with 'Only replacement image backgrounds; the saved automation type must match this tool.' Against a large update_*/prepare_*/generate_* sibling family, this lets an agent distinguish a recipe-replacement mutation from sample generation or activation.

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 implies the right context via preconditions ('the saved automation type must match this tool') and an exclusion ('Does not generate or publish'), but never names the alternatives an agent would weigh against — prepare_image_backgrounds_automation for new automations or generate_image_backgrounds_automation_sample for producing samples. Usage is inferable but not explicit.

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