Stitch multi-scene video

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

Annotations only declare false hints; the description adds meaningful behavior: 'Blocks until done' and 'Spends credits'. It also implies a render/creation operation, consistent with readOnlyHint=false. This gives the agent awareness of cost and synchronous behavior beyond the structured fields.

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 longer than average but every sentence is purposeful: purpose, usage conditions, model dependency, and behavior. It front-loads the core function and spends no words on fluff. Slightly verbose but well-structured and efficient.

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?

Covers the essential decision framework (when to stitch vs not), model limits from hermoso_capabilities, and behavior (blocking, credits). The scene object structure is only lightly described in the schema ('visual + optional voiceover/seconds'), but the description does not elaborate; however, the schema already provides that hint. Without an output schema, some return details are missing, but overall it's sufficiently complete for an agent to call correctly in most 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 coverage is 100% with each parameter described (model, voice, scenes, etc.). The description adds context about model max and duration defaults indirectly but does not go beyond the schema. Since the schema already documents parameters, a baseline 3 is appropriate.

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 a clear verb and resource: 'Render a multi-scene STITCHED video (≥2 scenes)'. It immediately differentiates itself from single-pass generation tools like generate_video/render_ad by stating the condition (spots longer than one clip). This precisely identifies the tool's unique role among many video-related siblings.

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?

Explicitly states when to use ('ONLY for spots LONGER than ONE clip of the chosen model') and when not to ('never stitch those'), and names the alternatives (generate_video/render_ad). It also references hermoso_capabilities for model-specific limits, giving concrete decision criteria. This is textbook usage guidance.

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