Load Super Source Look

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

Annotations already declare non-read-only, idempotent, non-destructive, closed-world, so the description is free to focus on semantics — and it does: it discloses what fields get overwritten, that source overrides only affect enabled boxes, and that cutToProgram pushes the result live. It does not cover failure behavior for an unknown look name, which is the main remaining gap.

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?

Purpose and restore-scope are front-loaded, then usage value, then args and examples — a sensible order. The Args block partially restates schema descriptions verbatim (name, ssrcId, cutToProgram), which is mild duplication, but the examples earn their space.

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 4-parameter, non-destructive, idempotent tool with full schema coverage and no output schema, the description gives enough to invoke correctly, including the override-only-enabled-boxes nuance. An agent would still be guessing about the response/confirmation and about behavior when the named look does not exist.

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%, so the baseline would be 3, but the description adds genuine meaning beyond the schema: the box-1-to-4 ordering constraint, that only enabled boxes are affected by 'sources', and a worked example array plus the default for ssrcId and cutToProgram. Only the ssrcId range (0-3) is left to the 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?

States a specific verb and resource ('Load a previously saved Super Source look and apply it to the ATEM') and enumerates exactly what state is restored (box positions, sizes, crops, art, border). This clearly separates it from siblings like atem_save_look, atem_list_looks, and atem_set_supersource_layout.

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?

Explains the primary use case (re-apply saved geometry) and the reuse pattern ('great for reusing the same layout geometry with different cameras/guests'), plus concrete trigger examples mapped to arguments. It stops short of explicitly naming the paired alternatives (atem_list_looks to discover names, atem_save_look to create them), so a 4 rather than a 5.

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