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

Beyond the annotations (readOnlyHint=false, idempotentHint=true), the description discloses the account-linking requirement, that it consumes plan usage, that the result is 'a queued job, not a finished video', and that it does not publish. The requestId retry contract ('preserve when retrying, including after a timeout; new UUID for changed content') meaningfully elaborates the idempotent hint.

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?

The core action and the confirmation prerequisite are front-loaded in the first sentence, and every sentence carries a rule rather than filler. The cost is that the remainder is an unstructured run of imperatives with no grouping by parameter or workflow stage, which makes it harder to scan for a 250-word description.

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-param creation tool with no output schema, the description covers the things an agent cannot infer from the schema: prerequisites, billing/account implications, the queued-job return semantics, non-publication, and retry identity rules. Combined with the highly self-describing schema (enums, const values, inline descriptions on confirmed/requestId/automaticBroll/workspaceId), the definition is complete enough to call 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 coverage is only 27% across 22 params, so the description has to compensate, and it does for the highest-risk fields: script must hold exact spoken words and never filmmaking directions, prohibitedChanges must stay separate from visible copy, generated motion shots capped at 15 seconds, aspectRatio must be preserved. However, large parameter groups (visualDirection, directions, audioLayers, assetSlots, steps, workspaceId) get no semantic treatment, so it only partly closes the coverage gap.

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 a specific verb and resource ('Create a private hosted video') plus the triggering condition ('after the user confirms the complete brief and plan usage'). It also actively disambiguates from siblings: 'This is the hosted brief contract, not VideoSpec or paired-announcement source' and 'Does not publish' separate it from scaffold_video_spec, prepare_announcement and any publish flow.

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?

Explicit when-to-use and when-not guidance is present throughout: confirmation and account linking are prerequisites, automaticBroll must stay off unless the user explicitly requests footage, narrationMode goes off for silent videos, publishTarget is a layout hint rather than a publish action. It even supplies an alternative-selection rule ('not VideoSpec or paired-announcement source') and retry guidance ('new UUID for changed content').

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