Playback control

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

With no annotations supplied, the description carries the full burden and does so well: it discloses that state is read back one frame after the command, what returns (playbackState, currentCue {no, name}, lastCue after Off), bridge version gates (0.32.0, 0.36.0), tag resolution rules (unknown or duplicate tag names send nothing), and that ReSync syncs phasers gradually rather than restarting the sequence. The remaining gap is failure behaviour for invalid non-tag targets, which is unstated.

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 equivalent commands are front-loaded, then progressively deeper detail, which is the right ordering. Some sentences are dense and clause-stacked — the tag-target sentence in particular nests resolution, addressing and readback into one breath — but no sentence is 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?

For a mutation-style playback tool with no annotations and no output schema, the description goes beyond the minimum by documenting return fields and version prerequisites. It is nearly complete; the shortfall is undefined error semantics for malformed or non-existent targets and unexplained enum values.

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 67%, and the description supplies the biggest missing meaning: the target grammar and the semantics of go, off, load and resync. The 'action' enum's remaining values (toggle, flash, select, release, learn, rate1, speed1) and the 'fade' parameter are left entirely to the schema, so it adds strong but partial meaning beyond structured fields.

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 ('Trigger a playback function on a sequence or executor') and immediately grounds it with equivalent console syntax ('Go+ Sequence 1', 'Off Executor 201', 'Load Sequence 1 Cue 5'). That framing lets an agent distinguish it from neighbouring tools like gma3_goto_cue or gma3_run_macro without opening the schema.

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?

The target-format catalogue ('Sequence 3', 'Executor 201', 'Page 2.201', 'Sequence 1 Cue 4', 'Master 3.1', 'Macro 5', 'Group 2') tells the agent exactly what shapes are accepted, and the resync paragraph scopes when that action applies. It stops short of naming when to prefer a sibling (e.g., gma3_goto_cue for cue navigation) or when not to use this tool.

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