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

Annotations already establish this is a non-destructive, non-open-world write. The description adds useful behavioral context in the coordinate convention (transform.y, with a 1080p example) and the available presets, but says nothing about defaults for start/duration/track placement or what happens if the target track has conflicting clips.

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?

Three short sentences, front-loaded with the action, with no filler. The preset enumeration duplicates the schema's enum, which is minor redundancy rather than harmful padding.

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 mutation tool with a large nested style schema, no output schema, and low schema description coverage, the description is thin: it omits timing/placement requirements and most styling parameters. An agent could call it for a basic title but would be guessing on duration, track targeting, and the text style object.

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 only 33% across 9 parameters, including a ~20-property nested text style object that is almost entirely undescribed. The description partially compensates by explaining the transform coordinate system with a concrete example and by enumerating the preset values, but leaves content, start, duration, opacity, trackId, and most style fields unexplained.

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?

"Add a text/title clip" names a specific verb and resource, and the preset list makes the scope concrete. It does not explicitly distinguish itself from neighbors like add_html_overlay or add_clip, but the object being created is 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?

There is no when-to-use or when-not-to-use guidance and no mention of alternatives (add_html_overlay, generate_captions, voice_captions). The preset menu tells the agent which style to pick, not which tool to pick.

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