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

Goes well beyond the readOnlyHint annotation by disclosing the refusal contract (SIMPLER_STUDIO_VISION_NONE), the reason (no platform model can view video frames), and the cost guarantee ('nothing is sent or spent'). This is exactly the kind of behavioral context annotations cannot carry, though the return format of a successful analysis is not described.

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?

Three sentences, front-loaded with the action, then the refusal contract and fallback. The parentheticals earn their space by clarifying vision scope and zero-cost behavior; only minor tightening is possible.

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 read-only, no-output-schema tool, the definition covers the core action, the unsupported-platform path, and the fallback strategy. What's missing is any hint at the shape of a successful result (e.g., a textual description per focus area), which would help the agent chain it into editing decisions.

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 67%, so the schema already documents project_id and focus (including the accepted values). The description echoes the describable aspects (subject, lighting, composition, mood) but omits 'pacing' and adds no format or default semantics beyond the schema, so it stays at baseline.

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 and resource ('look at a generated scene's actual frames (vision) and describe subject, lighting, composition, mood') and separates it from the assumption-based alternative. An agent can distinguish it from siblings like image.describe (still images) or studio.get_composition without opening a 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?

Explicitly says when to use it ('make editing decisions based on what you SEE, not assumptions') and, crucially, what to do when it refuses ('judge the scene from its prompt and the composition instead'). Both the positive case and the fallback path are named.

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