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

Annotations only give the generic safety profile (readOnlyHint=false, destructiveHint=false, openWorldHint=false), so the description carries the real burden and delivers: per-call cost (2 credits, 4 for before_after), the need to confirm budget via get_credits, and a non-obvious post-call side effect (the card updates on generation, so list_images is unnecessary). It does not cover failure/refund behavior or any permission constraints, which keeps it short of a 5.

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?

Front-loaded with purpose, then usage constraint, scope, cost, and return/side-effect in a tight sequence. Every clause earns its place, though the sentence packing purpose, cost and the list_images warning together is dense enough to slightly hurt scanability.

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-value details are not required; the description still explains the one non-obvious output behavior (the look appears on the card immediately). Together with cost, scope, and prompt constraints, an agent has everything needed to call this correctly.

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 100%, so the baseline is 3; the description adds genuine meaning on top by instructing that 'scene' must describe place/outfit/light and not re-describe the person, and by framing 'character' as the influencer id that scopes to own vs public cast. The other parameters are already self-documented in the schema.

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 ('generate a new look (reference image) of an existing AI influencer, same face, new setting'), which is precise enough to distinguish it from siblings like create_clip, create_scene_replace_clip, and retry_image. The parenthetical clarifies what a 'look' actually is, removing ambiguity about the output type.

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?

Explicitly says when to use it and how to fill the prompt ('describe only the place, outfit and light... never the person again'), states the supported scope (own influencers and the public cast), routes the agent to get_credits for confirmation, and explicitly says not to call list_images afterwards. Multiple when/when-not/alternative directives are present.

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