Start a photo picker session

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

Annotations already mark this as read-only, open-world, idempotent, and non-destructive. The description adds meaningful behavioral context beyond annotations: it returns a picker_uri, requires user interaction to complete, and involves a stateful pick session with timing constraints. The caveat about empty results is especially valuable for agents interpreting the tool's output.

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 front-loaded with the core purpose, then provides the required follow-up workflow, then the critical pitfall. Every sentence adds value: no filler, no repetition of the schema or title, and the most important instruction ('Give that URL to the user and stop') is prominent.

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 tool with no output schema, it fully explains the return value (picker_uri), the interactive nature, the required polling pattern, and the meaning of an empty result. It is complete enough for an agent to invoke and continue the workflow 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?

Schema description coverage is 100%: the single optional account parameter is fully documented in the input schema, including its default behavior and how to list accounts. The tool description does not add parameter-level detail, but none is needed because the schema already carries that burden. Baseline 3 is appropriate.

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?

Description uses a specific verb ('Open') and resource ('Google Photos picker') and clearly differentiates from sibling tools by noting it is 'the only way to reach media this app did not upload itself.' This distinguishes start_pick_session from search_library and other media-access tools.

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 explicit when-to-use guidance: use when the user needs media from their ENTIRE library, because the Library API cannot see anything else. Also gives a complete follow-on workflow: hand the picker_uri to the user, then call check_pick_session until ready, then list_picked_media. Directly warns against calling list_picked_media too early, which is actionable guidance.

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