contact_sheet

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

With no annotations, the description carries the disclosure burden. It explicitly warns about a key behavior: 'Slow, since every frame is a real render.' It also explains that stills are taken from the middle of each clip and that file paths are returned, providing useful context beyond a simple 'export' statement.

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 three sentences, each earning its place: the first states the core action, the second explains the intended use, and the third warns about performance. No filler or redundancy.

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?

The tool is moderate complexity with 3 documented parameters. The description covers the operation, expected output (file paths), use case, and performance caveat. It does not specify which sequence or project is used, but sibling tools like set_active_sequence imply the active sequence context, making this sufficient.

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 the schema already defines all parameters (output_dir, limit, track_index). The description adds context about what the output represents (one still per clip from the middle) but does not elaborate further on individual parameter meanings or constraints.

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: 'Export one still per clip on a video track, taken from the middle of each clip, and return the file paths.' This is a specific verb+resource combination that distinguishes it from siblings like export_frame (single frame) and export_sequence (whole sequence).

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?

It provides a clear use case: 'Read the images afterwards to judge a grade across the whole edit at once instead of one frame at a time.' This implies when to use it (evaluating overall grade) and contrasts with checking individual frames, though it does not explicitly name alternatives or state when not to use it.

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