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

Annotations already declare non-read-only, idempotent, non-destructive, closed-world behavior, so the bar is lower. The description adds genuine context beyond them: the exact rating values, the fixed reason vocabulary, the improvement purpose, and that the call is free of credit cost.

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?

One front-loaded sentence carries the action, the value mapping, and the reason vocabulary, followed by two short fragments that each add distinct information. Nothing is redundant or padded.

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 three-parameter, no-output-schema tool this covers the essentials — value semantics, the reason taxonomy, cost, and purpose. Only the origin of generation_id and any return behavior remain unstated, which are minor gaps at this complexity level.

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 coverage is 0%, so the description carries the burden, and it does well by defining the two legal rating values and listing all six reason strings that the schema leaves as a free-form string array. The gap is generation_id, whose expected source (a previously generated image's id) is never explained.

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 — thumbs up (1) or down (-1) on one generated image — and enumerates the rating scale inline, so an agent knows exactly the action and payload. It is clearly distinguishable from siblings like send_feedback or pick_image_version.

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?

Usage is implied (rate a generated image to help improve results) and the 'Free' note tells the agent it costs no credits, which is a useful selection signal. However, there is no explicit guidance on when to prefer this over send_feedback or pick_image_version, and no stated prerequisite that the generation_id must come from a prior generation.

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