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

The file parameter description adds valuable behavioral context: the operation forces a full H.264 re-encode into MP4 with audio copied and is among the platform's slowest operations on long videos. Annotations already mark the tool as non-read-only and non-destructive, so the description extends that with performance and output-format expectations.

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?

One lead sentence carries the action, resource, engine, and controls, plus a category tag. No filler or repetition.

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 4-parameter tool with no output schema, the definition covers the required input, optional text, and validation fallbacks; the file description also telegraphs the output container (MP4) and the performance cost. A return-value description would tighten it, but the behavior is sufficiently inferable.

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 100%, and the schema already documents defaults, ranges, enum values, and fallback behavior for opacity and position. The main description contributes only 'position and opacity control,' which duplicates existing schema detail rather than adding new semantics.

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 'Video Watermark' and uses a concrete verb, 'Overlay a text watermark onto a video using FFmpeg,' specifying the resource, the operation, and key controls. This is clearly distinguishable from siblings like photo_watermark and pdf_watermark, so an agent can select it without needing to inspect the schema.

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 'Video Watermark' framing and 'overlay onto a video' give clear context for when this tool applies, and the category tag narrows it to media. It doesn't explicitly name alternatives or exclusion conditions, but the video-specific wording makes the primary use case unambiguous.

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