Venice Video Retrieve / Status

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

No annotations are provided, so the description carries the burden. It discloses POST method, endpoint, return values (PROCESSING or COMPLETED), and authentication methods (x402 wallet auth, API key). This is reasonably rich behavioral context. However, it doesn't disclose rate limits, poll intervals, or whether retries are advised, and doesn't explain the delete_media_on_completion 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?

Three sentences covering purpose, status enum, endpoint, and auth — efficient and front-loaded. The first sentence clearly states the action. Minor redundancy: mentioning 'PROCESSING or COMPLETED' twice and endpoint twice slightly hurts conciseness, but overall it's compact.

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 status-check tool with no output schema and no annotations, the description provides solid context: status values, endpoint, auth methods. It's missing details on the undocumented delete_media_on_completion parameter and doesn't describe the exact response structure (does it return the media once COMPLETED?). It's adequate but leaves gaps, especially for a tool sitting in a larger video workflow with generate/complete siblings.

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 67% — model and queue_id are documented. The description reiterates that queue_id comes from venice_video_generate and model must be the same one used to queue, which adds useful cross-tool context. However, delete_media_on_completion (the undocumented param) is given no description anywhere, and the description doesn't explain how model relates to the generation call beyond 'same as used to queue'.

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 description states a clear verb+resource: 'Check status of a queued video job' with the status enum (PROCESSING, COMPLETED) and endpoint path (POST /v1/video/retrieve). It clearly distinguishes the retrieve/status tool from generate and complete siblings. However, it doesn't explicitly differentiate from venice_video_complete, and the title 'Retrieve / Status' is slightly ambiguous about whether it retrieves the output or checks status.

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?

The description makes the usage context clear: it's for checking status of a queued job, uses queue_id returned by venice_video_generate. It implies when to use it relative to the generate flow. However, it doesn't explicitly state when NOT to use it or name alternatives like venice_video_complete, so it lacks explicit exclusions.

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