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

The description adds substantial behavioral context beyond the readOnly/idempotent annotations: it details the two groups, explains that alive:false refs are dead and excluded, mentions usable signed URLs, and clarifies that chat attachments are not included. This goes beyond what annotations alone convey, providing essential operational details.

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?

Every sentence in the description earns its place: purpose, usage guidance, dead-ref handling, and chat-attachment exclusion. It is dense but not verbose, effectively communicating complex information in a compact, structured manner with no filler.

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?

The description is fully complete for a zero-parameter tool with no output schema. It explains the return structure (two groups with signed URLs), usage timing, how to use results with generate_video, and what is excluded. No critical information is missing, and the guidance is actionable.

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 complete. Per the guidelines, a baseline of 4 is appropriate. The description does not need to explain parameters, and it focuses on return semantics instead, which is not required but beneficial given no output schema.

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 staged references in Switch Studio and explicitly explains the two returned groups (refs and videoReferences). It distinguishes itself from siblings by mentioning specific contexts like the image-generation reference strip and the Omni/Image video tabs, making it clear which tool to use for staged references.

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?

Usage guidance is explicit: 'Call this before generate_image or generate_video whenever the user says "use my refs" or refers to images they staged in Studio.' It also provides an exclusion for chat-attached photos and names the alternative tool (upload_media), giving clear when-to-use and when-not-to-use instructions.

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