generate_seedance_video

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

With no annotations provided, the description carries full burden and delivers rich behavioral detail: it states task_type is forced and 'requesting another type has no effect; this is intentional, not an error', explains that user-supplied carriers are ignored, and discloses asset requirements and QA gates. It also clarifies the romanized_text gate and the implications for lip-sync, which goes well beyond a simple operation description.

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 long but employs clear section headers (HEBREW, Prompt, romanized_text, References) and bullet-like lists. Every sentence adds valuable information, avoiding filler. It is front-loaded with the core purpose and then organized by topic, making it scannable despite its length.

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 highly complex tool with 24 parameters, no annotations, and no schema descriptions, this description covers the essential workflow, special cases, and constraints comprehensively. It explains the Hebrew BVAC chain, romanization requirements, asset handling, and behavioral overrides. An output schema exists, so not needing to describe return values is acceptable. The description is thorough enough to guide correct invocation in almost all scenarios.

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 0%, so the description heavily compensates. It explains the meaning and usage of critical parameters: text, voice_id, audio_path, romanized_text, prompt, image_roles, other_roles, human_image_urls, other_image_urls, auto_upload_assets, task_type, wait, and image_urls as a legacy alias. However, parameters like duration, resolution, aspect_ratio, mode, service_mode, content_check, verify_speech, audio_urls, video_urls, and asset_retention_hours remain undocumented; while some are self-explanatory, the coverage is not complete.

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 opens with 'Generate a Seedance video' which clearly states the action and resource. It immediately distinguishes itself from siblings by adding 'auto-chain Hebrew BVAC lipsync when language is Hebrew', and contrasts with generate_kling_video and generate_seedance_first_last by specifying the video engine and Hebrew-specific behavior.

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 strong when-to-use guidance for Hebrew: it says 'this tool runs the ENTIRE BVAC chain itself; do NOT pre-build anything' and gives the audition flow with generate_elevenlabs_voiceover. It does not explicitly mention alternatives for non-Hebrew cases, but the Hebrew-specific context is clear and actionable. The guidance about not building carriers or uploading audio is a valuable exclusion.

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