Start EDL Logging

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

Annotations only say it's a non-readonly, non-idempotent, non-destructive local operation. The description adds substantive context beyond that: it captures switches from any source (hardware panel, Software Control, Claude, auto-switch) and the .edl file is rewritten after every switch so the on-disk copy is always current. It doesn't say whether a second call restarts or conflicts with an existing session.

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 behavior come first, then triggers, then parameters—a sensible front-loaded order with no filler prose. The Args block is long and partly re-states schema descriptions, which costs a little efficiency but carries defaults the schema omits.

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?

With no output schema, the description does explain the artifact (filename derived from title, always-current .edl on disk), which is what an agent needs to confirm success. It omits the return payload and the already-running case, leaving minor gaps for a 7-parameter stateful logging tool.

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 baseline is 3, but the description goes well beyond it: tc_source guidance ("use whichever matches the timecode recorded in the camera files"), the drop-frame default rule at 29.97/59.94, the actual output_dir default (~/Movies/ATEM EDLs), and a nested-object example for reel_names. These are decision-relevant details the schema truncates.

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+resource (start logging program switches on an M/E bus to a CMX 3600 EDL for DaVinci Resolve), plus the exact artifact produced. It clearly separates itself from the EDL siblings (atem_edl_stop, atem_edl_status, atem_edl_marker) which handle stopping, querying, and marking.

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?

Gives concrete trigger phrases ("start the EDL", "log this show", "start recording the cuts") that map user intent to this tool. It does not state when not to use it—e.g. what happens if logging is already active—nor does it point at atem_edl_stop as the companion call.

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