video_acceptance_eval

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

No annotations are provided, so the description carries the full behavioral burden. It discloses one trait (it does not approve / is non-mutating), but says nothing about permissions required, whether it writes any artifacts, what happens when a verdict fails the spec, or whether recalculation is needed between calls.

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 a single tight sentence with zero padding and the scope constraint is front-loaded, which is good. But it errs toward under-specification rather than conciseness — the brevity leaves core concepts undefined.

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 no explanation, but with no annotations, 0% parameter documentation, and heavy domain jargon, the description is not complete enough for an agent to confidently select and invoke this tool among many similarly named verdict/review/QC siblings.

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% for three required parameters, so the description must compensate and largely does not. Only loose hints exist ('exact-spec' vaguely maps to acceptance_spec_id, 'verdict' to verdict_ids); project_dir and the expected ID formats are entirely unexplained.

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 names an action (evaluate) and objects (exact-spec verdict, defect evidence) and adds the important constraint 'without approving anything,' so an agent can infer it is a non-approving review step. However, 'exact-spec verdict' is jargon that is never defined, and the tool is not differentiated from nearby siblings such as video_verdict, video_review_decide, or video_publish_gate.

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 explicit when-to-use, when-not-to-use, or alternative-tool guidance. The phrase 'without approving anything' weakly implies this is a pre-approval check, but the agent is not told what to do after receiving the evaluation or which sibling to call to actually approve or reject.

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