video_qc_vision

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

With no annotations, the description carries the full burden and does substantively disclose behavior: no executable VLM is available, require_vlm=True yields verdict=fail and blocked=True, and listed return fields. These are non-obvious operational details that prevent a failed invocation.

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?

Front-loaded with the core action, but slightly redundant: 'semantic vision QC is not evaluated' and 'Frame preparation is not a visual-quality pass' restate the same boundary in adjacent sentences.

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?

An output schema exists (so return values need not be fully explained, though the description helpfully names them), and for a 2-parameter tool the description covers the key caveats. The main gap is the undocumented input_path semantics.

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 0%, so the description must compensate. It explains require_vlm's effect (fail + blocked=True) but says nothing about input_path's expected value or format, leaving one of two parameters undocumented in both description and schema.

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?

States a specific verb+resource: 'Prepare keyframes for visual review,' and explicitly scopes out semantic vision QC, which differentiates it from QC siblings like video_quality_check and video_design_quality_check. The purpose is clear, though the negation-heavy framing adds some ambiguity about what the tool actually produces.

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?

Usage is implied (use it when you need keyframes prepared before a review step), and it usefully flags that require_vlm=True will fail. However, it names no alternatives among the many QC/review siblings and gives no explicit 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.