video_stitch

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

With no annotations provided, the description carries the full burden of behavioral disclosure. It goes far beyond basic safety by detailing the hard cut between clips, preservation of each clip's audio, scaling of different-sized clips, optional music/subtitles, ffmpeg requirement, dry_run mode, and the exact return value or error format. This is rich, actionable context.

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 a single, logically ordered paragraph that front-loads the core purpose, then covers usage, options, output, and requirements. Every sentence contributes meaningful information; there is no filler or repetition. The structure is clear and easy to scan 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?

Given the tool's complexity (5 params, no output schema, no annotations), the description is remarkably complete. It explains the return format, prerequisite (ffmpeg), error behavior, dry_run capability, and integration with video_generate. Nothing essential is missing for an agent to select and invoke it 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?

The schema already covers all five parameters with 100% description coverage, so the baseline is 3. The description adds extra semantic value by explaining the intended use of music and subtitles, clarifying clips can be local paths or URLs from video_generate, and describing the dry_run behavior. While it doesn't introduce new parameters, it enriches the meaning beyond the schema.

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 clearly states the tool's function: joining finished video clips into one file in order. It explicitly distinguishes itself from video_generate by noting it 'does not generate new video,' which is essential for sibling differentiation. The verb and resource are specific and unambiguous.

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 when-to-use guidance: 'Use it to build a video longer than a single model clip' with a concrete workflow ('generate the shots with video_generate, then stitch them'). It also gives clear when-not-to-use cases: 'Do NOT use it for a single clip, or for a batch of clips meant to stay separate.' This is exemplary guidance.

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