Look at a scene

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

Annotations already declare readOnlyHint=true, so the safety profile is covered. The description still adds value by clarifying that the call returns viewable image content (not a URL or metadata blob), which tells the agent what kind of payload to expect. It does not discuss image size, format, or failure behavior for stale ids.

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?

Two short sentences, no redundancy, and the core purpose is front-loaded ahead of the input-sourcing hint. Every clause earns its place.

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 one-parameter read tool with no output schema, the description covers purpose, the nature of the return value, and how to supply the input. Nothing an agent needs to invoke it correctly is missing.

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 100% for the single parameter, so the baseline is 3. The description goes beyond the schema's bare 'The thumbnail's id.' by telling the agent where to obtain a valid id, which is the key semantic gap for this argument.

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 ('Fetch the actual image of a scene thumbnail') and adds the agent-facing rationale ('so you can see what is in the shot'). This clearly separates it from siblings like search_scenes or get_video_scenes, which return ids/metadata rather than the image itself.

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 tells the agent the prerequisite step and names three concrete sources for thumbnailId (search_scenes, search_scenes_semantic, get_video_scenes). It lacks any when-not-to-use or cost/latency caveat, but the usage context is unambiguous.

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