Generate Media Contact Sheet

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

The description adds meaningful behavioral context beyond the annotations: it refuses to overwrite an existing output, performs disk verification, and does not modify Premiere or the source. This clarifies the tool's non-destructive but file-writing nature, with no contradiction against the provided annotations.

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?

Two sentences, both dense with useful information: core action, output type, sampling strategy, overwrite behavior, and side-effect guarantee. There is no filler or repetition of schema content.

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 description is largely sufficient: it covers required inputs, output type, sampling behavior, and side-effect safety, while the full schema and output schema cover parameter details and return structure. It does not describe failure modes or whether Premiere must be open, but those gaps are minor given the support from structured metadata.

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 already documents all five parameters with descriptions, so the baseline is 3. The description adds extra semantic value by indicating that output_path must point to a non-existent file (refuses to overwrite) and that frames are evenly sampled from the source, which helps understand how rows/columns relate to the output.

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 uses a specific verb+resource pair: it generates a disk-verified PNG contact sheet from evenly sampled source frames. It also distinguishes itself from single-frame exports by emphasizing the contact-sheet output and explicitly stating that it does not modify Premiere or the source.

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 intended use is implied clearly: call this when you want a contact sheet of sampled frames from a local video file. However, the description does not name alternatives or provide explicit when-to-use/when-not-to-use routing, aside from the overwrite refusal.

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