create_video

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

With no annotations, the description carries the full behavioral burden. It discloses the async nature, that it returns video_id and must be polled with query_video, fixed 720P size, seconds range, and limits on images/audios. It does not mention rate limits or error behavior, but the critical async/polling behavior is transparent.

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 description is well-structured with trigger phrases, mode explanations, and examples. It is somewhat long but every section adds value: the Chinese triggers, mode conditions, and examples all serve the agent. Front-loading the async behavior and polling requirement makes key information immediately visible.

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 11-parameter tool with no annotations and no output schema, the description covers the core usage well but leaves gaps. It omits aspect_ratio, seed, api_key, and base_url semantics, and does not document error cases or authentication requirements. The return value (video_id) is stated, and polling is explained, so it is adequate but not fully complete.

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?

Since schema description coverage is 0%, the description must compensate. It explains mode, prompt usage, seconds, images, audios, first_frame, and last_frame with concrete examples. However, it does not explain seed, api_key, base_url, or aspect_ratio, which are significant parameters. The aspect_ratio enum values are visible in the schema, but their meaning is not described.

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 specific verb and resource: 'Create an async agnes-video-2.5-flash task' and notes it returns video_id for polling. It clearly differentiates from query_video by naming it as the polling counterpart. However, it does not distinguish itself from the sibling generate_video, which is also a video-creation tool, so it lacks full sibling differentiation.

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 provides explicit trigger phrases (中文触发), recommends async to avoid IDE timeout, and explains when each mode applies: text, keyframe, and reference. It also specifies required inputs per mode (e.g., first_frame/last_frame for keyframe, images/audios for reference). It does not explicitly state when not to use this tool versus generate_video, but the guidance is clear enough for most cases.

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