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

Annotations already declare idempotentHint=true, destructiveHint=false, and readOnlyHint=false, so the mutation/safety profile is covered. The description earns credit by adding behavior beyond that: the saved draft is inactive, consumes no credits, and triggers no content generation or publish, which an agent cannot infer from the annotations alone.

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, front-loaded sentences with no filler; the 'does not generate/spend/publish' clause is efficient. The final clause is slightly awkward but still earns its place by specifying the automation type constraint.

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 explained, and the annotation profile plus the credit/publish disclaimer cover the operation's side effects. However, for a tool whose input is a large required nested recipe with zero field descriptions, the description leaves the agent without guidance on the payload it must assemble.

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% for three parameters, including a deeply nested recipe object with many sub-properties (mode, brandColors, attachmentIds, caps, cads). The description adds no information about any of them, so it does not compensate for the total coverage 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?

The description states a concrete action (saving an inactive review draft) and scopes it to a specific automation type ('only recolored source images'), which separates it from the other prepare_* siblings. It is one notch below 5 because the phrasing 'the saved automation type must match this tool' is indirect rather than naming the recolor type outright.

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 context by clarifying that the draft is inactive and that no generation/credits/publishing occur, but it never names the alternatives (update_recolor_automation, activate_recolor_automation) or states when to prefer this over them. Usage is implied rather than explained.

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