get-selected-photos

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

No annotations are provided, so the description carries full burden. It discloses read-only behavior, reliance on AppleScript, requirement for Photos.app running with a visible selection, macOS Automation permission, and the fact that it never launches Photos itself. It also explains the notFound behavior for uncheckpointed imports.

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 most critical usage guidance, then flows into return values and caveats. Every sentence earns its place, providing dense, non-redundant information. Although it is longer than the calibration example, the extra length is justified by the tool's behavioral complexity and lack of annotations.

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 no annotations and an output schema (whose details are not needed because the description summarizes return values), the description fully covers prerequisites, error conditions, permissions, and integration with sibling tools. It leaves no significant gap for an agent to invoke 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 tool has zero parameters, so the schema is trivially 100% covered. Per rubric, a 0-param tool gets a baseline of 4. The description adds no parameter-specific semantics but appropriately explains the return values and integration points, which is sufficient when no parameters exist.

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 reads the user's selected photos from Photos.app, using specific phrases like "GUI-selection bridge" and "returns the same photo summaries as query". This identifies a specific verb-resource pair (get selected photos) and distinguishes it from sibling tools like query, get-photos, and export.

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 provides use cases ("Use when: the user says 'these photos'") and exclusions ("Do not use when: you want to FIND photos by criteria — use query"). It also names alternative tools to feed the UUIDs into, giving clear guidance on when to use this tool versus siblings.

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