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

Annotations already declare destructive=true, idempotent=true and readOnly=false, but the description adds the concrete consequence: the recipe is replaced and the reviewed sample is invalidated, plus the constraint that no generation or publishing happens and only matching recolor automations are accepted. It does not cover auth/permission needs, but the key destructive side effect is disclosed.

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 action before the caveats. The trailing fragment 'Only recolored source images; the saved automation type must match this tool' is terse to the point of slight ambiguity, but there is no filler.

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?

The tool is a destructive mutation with annotations covering its safety profile and an output schema covering return values, so the description need not repeat those. It supplies the essential behavioral facts (recipe replacement, sample invalidation, no generation/publishing, type constraint); the main omission is parameter-level detail, which overlaps with the parameter semantics gap.

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 five required parameters, including a deeply nested recipe object, yet the description explains none of them - not revision, idempotencyKey, brandId, or any recipe field. The only indirect parameter signal is the automation-type constraint tied to automationId. For a 0%-coverage multi-parameter mutation, this is a substantial 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 and resource: replacing the automation's recipe. It also scopes the tool to 'recolored source images' and requires the saved automation type to match, which separates it from the many sibling update_*_automation tools without the agent opening their schemas.

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' rules out a common mistaken invocation of the sibling generate/publish tools, giving clear when-not guidance. It stops short of naming the actual alternatives (e.g. generate_recolor_automation_sample or prepare_recolor_automation), so routing is implied rather than explicit.

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