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

Annotations only declare a generic write/open-world profile; the description discloses substantially more: asynchronous return with status 'rendering', the generation_id handle, expected latency ('usually under a minute'), per-second billing, and idempotency guidance. This is exactly the behavioral context annotations cannot convey.

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?

Efficient and front-loaded: the action and its economics lead, then the async contract, then the follow-up routing rule. Every sentence earns its place, though the parenthetical model/resolution clause is slightly dense.

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?

With no output schema, the description correctly compensates by describing the immediate return (status 'rendering' plus generation_id) and where the result surfaces. An agent has everything needed to call it and handle the response 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 prompt, seconds, and asset_id are fully documented in the schema itself. The description only echoes the asset_id/generation_id flow rather than adding syntax or format detail, so the baseline 3 applies.

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+resource ('turn an image into a short video clip') and adds concrete scope: model (Grok Imagine Video), 720p, with sound, billed per second. It is immediately distinguishable from siblings like generate_image and get_video.

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 routes follow-up usage elsewhere ('call get_video with that generation_id') and gives a clear when-not ('Do not call animate_image again for the same request'). Both the alternative and the exclusion condition are named.

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