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

Annotations already declare destructiveHint=true, openWorldHint=true and idempotentHint=false, so the safety and side-effect profile is covered. The description adds useful defaulting behavior (Gemini Omni 1.1 Flash fallback, server-side default workspace), but says nothing about paid generation cost, latency, or failure/recovery behavior beyond what the schema's maxCostUsd and idempotencyKey fields already state.

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?

Purpose, trigger phrasings and prerequisite are front-loaded before the fallback details, and every sentence carries information. The long model-provider enumeration is verbose but does real selection work by matching user-named providers.

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 22-parameter, one-required-parameter tool with an output schema and 95% schema coverage, the description supplies the missing high-level context: what triggers it, the storyboard-approval gate, and the default-resolution rules. Cost, rate limits and async/return behavior are left to the schema and output schema, which is acceptable here.

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 95% across 22 parameters, so the schema already carries the parameter semantics and the baseline is 3. The description's only added parameter value is the default-model and omitted-workspaceId behavior, which is largely restated from the schema descriptions of `model` and `workspaceId`.

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 first sentence states a specific verb and resource (generate an AI video through Sequencer) and the second enumerates the user phrasings and model providers it covers, which is genuinely useful for matching. It stops short of naming its nearest sibling (generate_shot_video) so the agent must infer the boundary between standalone generation and shot generation.

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?

It gives a clear when-to-use trigger (any request to make/create/animate/render a video, or naming a supported model) plus a real prerequisite for project builds: only after shot stills/storyboard are approved. It also resolves two common unknowns (default model, omitted workspaceId). No explicit when-not guidance or named alternative tool is offered, so it is strong context rather than full routing.

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