start_photo_picker

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 discloses the interactive nature (browser link, picker's search box), the Google limitation on programmatic access, the return of a sessionId for later use, and the account connection requirement. This exceeds typical transparency and fully informs the agent of the tool's behavior.

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 three sentences, front-loaded with the main purpose. Each sentence adds distinct value: what it does, how to use it interactively, and what to do next. There is no repetition or fluff, making it concise and well-structured.

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?

Given the tool has no input schema, no output schema, and no annotations, the description fully compensates by explaining the complete workflow: opening the picker, receiving a link, using the search box, selecting photos, and passing the sessionId to create_video_assembly. It also notes the account requirement, making it sufficiently complete for an agent to use the tool correctly.

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?

The input schema has zero parameters, so the baseline is 4. The description adds context about the implicit prerequisite (connected Google account) and the output sessionId, which compensates for the lack of schema details. Although not directly about input parameters, it provides necessary semantic context for using the tool.

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 clearly states the tool's function: 'Open a Google Photos picker to choose B-roll for create_video_assembly.' It specifies the action (open picker), the resource (Google Photos), and the purpose (choose B-roll for create_video_assembly), distinguishing it from sibling tools like suggest_clips or list_connections.

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?

The description provides explicit when-to-use context: pick B-roll for create_video_assembly. It also gives a when-not/alternative: 'Google does not allow listing or searching your albums programmatically — so use the picker's OWN search box to find an album or topic.' It further instructs the next step of calling create_video_assembly with the returned sessionId, and notes the prerequisite of a connected Google account.

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