video_qc_narrative

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

No annotations and no behavioral disclosure at all in the description: no mention of whether it reads or writes, what it returns besides the implied heuristic, what output looks like, or any side effects. The entire behavioral burden falls on the description, and it carries none of it.

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?

It is short, but that shortness is under-specification rather than conciseness: a fragment with an unexplained internal code ('P3.4') that probably means nothing to an agent. No structure, no front-loaded statement of action.

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 QC tool in a very crowded QC/sibling namespace, the definition is far too thin. Even though an output schema exists (which relieves some return-value explanation), the agent still lacks purpose, usage context, parameter meaning, and behavioral profile needed to invoke it correctly.

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 single required parameter input_path has 0% schema description coverage, so the schema does not explain it and the description does not either – the string 'input_path' is mentioned nowhere. With a low-coverage schema, the description was obligated to compensate and does not.

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 'Narrative/retention heuristics incl. first-15s window (P3.4)' is a fragment, not a sentence with a verb and resource, and it never states what the tool actually does (evaluates? scores? reports?). It cannot be distinguished from siblings like video_qc_vision or video_metric_qc without opening 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?

No when-to-use guidance, no alternatives named, no exclusions, no prerequisites. Given the dense family of QC tools (video_quality_check, video_metric_qc, video_qc_vision, video_release_checkpoint), this silence leaves an agent unable to route correctly.

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