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

Annotations already declare this is a non-read-only, non-destructive, non-idempotent, closed-world mutation, so the safety profile is covered. The description adds genuinely new information beyond them — the cost model ('15 credits per second') and the continuation-from-last-frame behavior — but says nothing about whether the original asset is modified or a new asset is produced, which matters for a non-idempotent, paid call.

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?

Two short sentences, front-loaded with the action and followed by the cost signal. Nothing is padded and no sentence is wasted.

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 six-parameter, paid, non-idempotent mutation with no output schema, the description is thin: it does not say what is returned (new file key vs. mutated asset), how repeated calls compound cost or frames, or what the undocumented width/height/duration parameters mean. An agent could invoke it but not reliably chain the result.

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 50%: video, prompt, and assetId are documented in the schema, while width, height, and duration are bare. The description does not fill that gap, though 'credits per second' indirectly signals that duration is measured in seconds and drives cost, which is real added meaning.

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 ('Continue an existing video asset') plus the mechanism ('from its last frame'), which is enough to distinguish it from generate_video without opening the schema. It never names the sibling explicitly, so differentiation is inferred rather than stated.

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 phrase 'existing video asset' implies a precondition, but the description gives no explicit when-to-use versus generate_video, no statement that the asset must already exist, and no guidance on chaining extensions. The agent must infer the routing decision from the sibling list.

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