Draw box

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 states that it draws on the video and can be time-limited, but does not mention whether the original file is modified, if a new file is written to output_path, or any potential side effects like overwriting. This is a significant gap for a mutation tool with no annotation safety hints.

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 two sentences, front-loaded with the primary action ('Draw a rectangle outline or filled box'), and every word adds value. There is no fluff or repetition of schema fields, making it highly 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?

Given 11 parameters, 100% schema coverage, and no output schema, the description is reasonably complete for selecting the tool, but lacks important operational context like whether it requires output_path, how it interacts with audio or other video properties, or what the visual result looks like beyond a basic rectangle. It is minimal but not fully inadequate for a complex tool.

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 covers 100% of parameters with descriptions, so the baseline is 3. The description adds minor value by calling out the outline vs. filled box option (which already exists in the 'fill' param) and the time-range limitation (also already in 'start'/'end'). No additional semantic depth beyond what the schema provides.

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 purpose: drawing a rectangle outline or filled box on a video, with specific use cases of highlighting or redacting a region. This distinguishes it from sibling tools like blur_region, which would redact via blurring, and crop_video, which modifies the frame rather than adding an overlay.

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 clear context for when to use the tool: when the goal is highlighting or redacting a region. However, it does not explicitly mention alternatives or when not to use it, such as 'use blur_region if you need to obscure content without a visible box outline.' This leaves room for ambiguity but gives a solid contextual cue.

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