analyze_video_music

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

With no annotations, the description carries the full burden of behavioral disclosure. It explains the dual backend (Gemini when key is set, else local heuristics) and guarantees search_queries are always populated even for weak analysis. However, it does not mention whether the operation is read-only, has side effects, or any rate limits. The analysis nature is implied but not explicitly flagged, so a 3 is appropriate.

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?

The description is compact and front-loaded with the core purpose. It then lists platform_hint values, explains backend behavior in one sentence, and clarifies extra_notes. Each sentence adds distinct value with no filler, making it easy to scan.

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?

The output schema covers return values, so that is handled. The description includes backend behavior and parameter hints, but misses explicit usage routing to siblings and any prerequisites (e.g., that the video must already be ingested). Without guidance on when to choose this over recommend_bgm or search_music, the context is incomplete.

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 platform_hint by listing allowed values and clarifies extra_notes as a hint, not a replacement. However, asset_id is only described by its name, leaving its origin (e.g., from ingest_video) unspecified. While two of three params are clarified, the one required param lacks semantic detail, justifying a 3.

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, actionable purpose: 'Produce a structured VideoSonic profile for BGM matching.' This clearly identifies the resource (video) and intent (BGM matching), distinguishing it from siblings like search_music (search for tracks) or recommend_bgm (suggest music). The verb 'produce' and the structured-output nature make it unambiguous.

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?

Provides context like platform_hint and extra_notes, but does not explicitly state when this tool should be used vs alternatives. No mention of prerequisites (e.g., that asset_id must come from ingest_video) or conditions that would favor another sibling (e.g., search_music). The guidance is entirely implicit, leaving the agent to infer usage.

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