video_review_run

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

No annotations are provided, so the description carries the full burden. It implies a non-destructive evaluation ('watching guardrail', 'offline') but never states whether it writes artifacts, what a failing floor does, or what permissions are needed. An output schema exists, which lightens the return-value burden, but side-effect and failure semantics are unstated.

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?

A single short sentence with no filler, so it is economical, but the compression produces near-unparseable jargon rather than front-loaded clarity. Brevity here is under-specification, not conciseness.

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 two-parameter tool with zero schema description coverage and no annotations, the description should explain the required input and the policy object's role. The output schema is the only structured aid available, leaving the calling contract largely opaque.

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 description coverage is 0%, so the description must compensate for both parameters. It obliquely covers 'policy' via 'review policy' but says nothing about the required 'input_path' (what file/artifact, what format). The required parameter is entirely undocumented.

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 phrase 'run offline metric floor under a review policy' gestures at a guardrail/evaluation action but never names a concrete resource or outcome, so an agent cannot say what it produces. It does hint at a review-policy context that overlaps with siblings like video_review_decide and video_metric_qc, but the differentiation is accidental rather than stated.

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 guidance, no preconditions, and no mention of the many review/metric siblings (video_review_decide, video_metric_qc, video_acceptance_eval). The word 'guardrail' implies a gating context but nothing tells the agent when this is the right tool.

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