evaluateVideoWithDOVER

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

With no annotations, the description carries the full burden. It does disclose useful behavior: analysis runs on a bundled local ONNX model (no external service), and it lists the full output surface, implying a non-destructive read. However, it omits runtime/latency expectations for a video model, failure modes for unsupported files, and what happens when videoPath has no audio and audioPath is omitted.

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 action and model, followed by the return payload in one dense sentence with no filler. The parenthetical model expansion is verbose but informative; nothing is repeated from the schema.

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?

No output schema exists, and the description compensates by enumerating every returned score and diagnostic field, which is exactly what the agent needs to interpret results. Remaining gaps are operational (latency, error cases, audio-absent behavior) rather than about what the tool produces.

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 100%, so the schema already documents all four parameters, giving a baseline of 3. The description adds only indirect value by naming the Audio-Visual Beat Sync Score, which hints at audioPath's role, but it does not clarify startTime/endTime behavior (e.g., how segment scores are aggregated over a partial range).

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 ('Score') plus resource ('rendered video') and names the exact model (DOVER-Mobile, ConvNeXtV2-Femto-3D ONNX) and supported formats. It also enumerates the returned score types (Technical, Aesthetic, Fused, Audio-Visual Beat Sync), which makes it unmistakable against siblings like analyzeAudioRhythm or inspectFrameAestheticsAndClipping.

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 only implied: 'rendered video' signals it belongs after export/preview rendering. There is no explicit when-to-use / when-not, and no routing against clearly adjacent siblings such as inspectFrameAestheticsAndClipping (single-frame clipping/aesthetics) or analyzeAudioRhythm (beat analysis), leaving the agent to infer which to pick.

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