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

Annotations already tell the agent this is not read-only, not destructive, and not idempotent, but the description adds genuinely new context: the tool is PAID and cheap, synchronous with an inline return (no jobId), and returns a { hint, cost } object. It also discloses the failure mode for wrong asset types. These go well beyond the structured annotations.

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?

Four dense sentences, each earning its place: cost/sync behavior, what it reads and writes, when to use it, and the type restriction. The most decision-relevant details (paid, synchronous, inline return) are front-loaded, and there is no 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?

The description covers the return shape, cost, synchronization, input purpose, supported asset type, and points to the consuming tool. The schema covers parameter details and dryRun behavior. It is complete enough for an agent to call correctly, though a mention of what happens on failure beyond 400 would round it out.

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 schema already documents parameters in detail. The description adds the crucial usage context that 'pairs' are only context ('nothing is generated from them') and that the output maps to animate_asset's motionHint, but it does not add syntax-level meaning beyond the schema. A 3 is appropriate per the baseline rule.

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 specific verb ('suggests'/'writes') and resource (motion hint for a staged asset), and distinguishes it from siblings by tying its output to animate_asset's motionHint. It also explicitly names the asset type it supports, so an agent can tell it apart from animate_asset and other creation tools.

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?

The description gives a concrete when-to-use: 'Use it when you are about to spend 300 credits on a default video and are unsure what to write.' It also clearly excludes unsupported asset types ('any other type answers 400') and implies the alternative (proceeding without a hint). This is explicit and actionable.

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