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

Goes well beyond the annotations (readOnlyHint=false, destructiveHint=false, idempotentHint=true, openWorldHint=true): it states account linking is required, that the return is a queued job rather than a finished video, that it never publishes, and that retrying with the same requestId is the correct recovery after a timeout. The retry/UUID rule converts the idempotent hint into actionable behavior.

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?

Front-loaded with the core action, but the remainder is an undifferentiated run-on of policy rules with no grouping or bullet structure. Several sentences restate what is already in the schema (automaticBroll default, publishTarget not publishing), spending length on redundant 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 a 22-parameter creation tool with no output schema, it covers the essentials: the mutation is a queued render, it never publishes, retry identity, and the main content-integrity constraints. It does not mention how to follow up on the queued job (get_video_render_status), which is the one operational gap an agent would need.

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 100%, so baseline is 3, but the description adds cross-field meaning the schema cannot express: requestId identity rules, that publishTarget is a layout hint rather than authorization, that narrationMode off implies explicit scenes with no script, and that visual exclusions belong in scenes[].generationContract.prohibitedChanges rather than visible copy. A few of these repeat the per-field schema text, limiting the added value.

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 opening sentence names the specific action (create a private hosted video and start rendering) plus its gating condition (user confirms the brief and plan usage). It explicitly disambiguates from siblings by stating it is the hosted brief contract, not VideoSpec or the paired-announcement source, which maps onto scaffold_video_spec and prepare_announcement.

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?

Clear context is given: requires account linking, must come after user confirmation, and it is the wrong choice for VideoSpec or paired-announcement work. Conditional guidance is offered for automaticBroll (auto only on explicit request) and requestId reuse. It never explicitly says which sibling to use instead when a user has not yet finalized a brief (e.g. propose_video_storyboard or scaffold_video_spec), so no full when/when-not mapping.

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