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

With no annotations provided, the description carries the full burden and does so: nothing is saved, no name is consumed, one image is billed from the monthly allowance per picture, Pro tier is required, only public https links are accepted (not pasted images), and identifiable real people must never be reproduced. These are exactly the mutation/cost/policy facts an agent needs before calling.

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 the unsaved-preview constraint before the alternative and the cost/tier caveats, so a skimming agent still gets the essential contract. It is dense to the point of being run-on in the middle workflow sentence, but no sentence is 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?

For a non-destructive preview tool with no output schema and no annotations, the description covers lifecycle, persistence, billing, tier gating, reference-image handling and content policy. Nothing needed to invoke it correctly or explain the result to a user is missing.

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 100%, so baseline is 3, but the description adds genuinely new meaning: reference_image_url must be a public https link rather than a pasted image, reference_mode selects between recreation ('same') and style transfer ('style'), and style maps to style_preset on create_video for downstream consistency. Only 'description' length/content is left entirely to 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 ('Create a recurring character for the user's videos') plus the defining constraint ('WITHOUT saving yet') and the concrete output ('a full-body figure on white in the chosen style preset'). It explicitly separates itself from create_character and save_character, so an agent can route correctly without opening any schema.

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?

Gives explicit when-to-use ('Prefer this over create_character whenever the user wants to see the character before it is saved') and a full branch map of follow-ups: save_character with a name, change_character for edits, or start again. Also states the access tier ('Pro and above') and the cost condition up front.

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