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

Annotations already declare destructiveHint=true and idempotentHint=true; the description earns credit by naming what is destroyed ('replacing its previous bank') and by imposing content preconditions (distinct, owned, ready, 10–15s). It does not say what happens if the supplied generations fail those preconditions (error vs. silent skip).

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 compact sentences with the action and constraint front-loaded, then production guidance, then downstream reuse. Slightly jargon-dense (omni-human-1.5, Long Talk runs) but every sentence carries information.

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?

Output schema exists so return values needn't be described, and the destructive mutation is explained. Remaining gaps are secondary: whether generations are referenced or copied, and whether existing Long Talk outputs are affected by the replacement.

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 must carry the load, and it does: subject_id is a character Subject and generation_ids must be two or three distinct, owned, ready 10–15 second generations. That adds ownership/readiness/duration semantics the schema's bare minItems/maxItems does not convey; only UUID format detail is left 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 (Save) and resource (a bank of 2–3 video generations bound to a character Subject), plus the replace-in-place semantics. An agent can distinguish it from get_subject_performances or update_subject without opening the 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?

Explains the lifecycle role of the bank: base takes are made once with omni-human-1.5 using varied framing and neutral speech, and later Long Talk runs reuse them. That is clear use-context, though it doesn't state explicit exclusions (e.g., don't call when a valid bank already exists, or route to get_subject_performances for inspection).

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