video_analysis

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

With no annotations, the description carries full burden. It discloses the key behavioral traits: output is text (not video), parallel execution for batches, potential rejection of very large files due to inline analysis, and dry_run for previewing without spending. It also implicitly notes cost by referencing 'spending' in the dry_run context. No contradictions and substantial transparency.

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 front-loaded with the core purpose, then delivers use cases, batch advice, a caveat, and dry_run in a logical flow. Every sentence carries necessary information without redundancy. It is packed but well-organized, striking a good balance between detail and brevity.

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 tool with no output schema and no annotations, the description adequately covers what an agent needs to call it: it names the input types, explains the output type ('text'), covers the batch scenario, flags the large-file risk, and explains dry_run. Missing details like error handling or exact response format are not critical given the simplicity of the output promise.

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%, so all parameters are already documented. The description adds practical meaning beyond the schema: for 'requests' it explains parallel run and the mutual exclusion with 'video', for 'prompt' it gives an example and the default behavior if omitted, and for 'dry_run' it clarifies what the preview returns. This adds genuine value, though the baseline of 3 is raised slightly.

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 ('Watch') and resource ('one or more videos') and clearly defines its output ('returns text'). It distinguishes from siblings like video_generate by explicitly saying 'not new video', and from image_analysis by the video domain. It also mentions transcription, which overlaps with the transcribe sibling but clarifies it happens as part of video analysis.

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 use cases: 'Use to read a clip before generating or matching it, to describe what happens in it, or to transcribe what is said.' It also gives guidance on batching via the 'requests' parameter and explains when to prefer it. It mentions inline analysis and the large-file caveat, and describes dry_run for previewing. Clear situational guidance.

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