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

Annotations only declare mutability and open-world traits; the description adds genuinely new behavior: it is asynchronous ('Starts a background job'), it consumes credits, and it returns a project id that must be polled. That is the crucial operational context for a write tool. It stops short of covering failure/refund behavior or cancellation.

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 short sentences: what it does, when to pick the sibling instead, then the async/cost consequence and next step. Front-loaded and free of repetition of schema content.

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 an 8-parameter, nested-schema, enum-heavy tool with an output schema present, the description supplies exactly the non-schema essentials: purpose, sibling routing, asynchronous job semantics, credit cost, and the follow-up tool. Nothing needed to invoke it correctly 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 description coverage is 88%, with detailed per-model constraints on audio, model, resolution, end_seconds, aspect_ratio and references. The description only alludes vaguely to 'optional supported reference inputs and model settings' and adds no meaning the schema doesn't already carry, 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 and resource ('Generates a video from a text prompt') plus the scope of optional inputs and model settings. It explicitly distinguishes itself from create_video_from_image, so an agent can route between the two without opening either 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 a clear selection rule ('To animate an existing starting image, use create_video_from_image') and names the required follow-up (wait_for_video_project). It does not address the many other video-producing siblings (create_video_from_audio, create_animation, edit_video), but the primary branching decision is covered.

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