marker_add_transition_timeline

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

There are no annotations, so the description carries the full burden. It goes beyond just saying 'adds' by explaining structural verification (produces valid TransitionTimeline with bound child objects, confirmed via isValid:false without them) and what crossfade_length does (overlaps by seconds, making FMOD blend them). It also discloses limitations: the exact blend hasn't been audibly verified and there's no scripted way to listen, which is honest about behavior. It misses some things like whether it's idempotent or what happens on failure, but given the depth of disclosure, a 4 is justified.

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 relatively long, but every sentence adds value: the first sentence defines purpose, the second provides structural verification and a caveat, the third describes parameters. It is front-loaded with the core purpose. Some redundancy exists (repeating 'source+destination sound pair'), but overall it's dense and not padded. Could be slightly tighter, but it's structured well with a clear Args block.

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 the complexity (a feature that creates crossfades and requires specific bindings) and the lack of output schema or annotations, the description is quite complete: it explains what is created, correct binding requirements, how timing works, and what to do if the blend is wrong. It doesn't mention potential failure modes for invalid inputs beyond the structural verification, but for an agent, this is sufficient to call correctly. Minor gaps like whether it modifies or replaces existing timelines, but overall it's close to complete.

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 description coverage is 0%, meaning the schema itself does not describe parameters in text—only names and types. The description compensates significantly: it explains transition_target (guid of the target marker/region type), audio_track_target (the track being looped), and crossfade_length (overlap in seconds, default 1, must be >0, larger = smoother). It adds meaning beyond the raw names, but there are only 3 params and they are fully explained, so this is strong relative to baseline. However the tool has 'Args:' section not in the formal schema, so the description is the primary source, earning a 4. But the calibration note says baseline 3 for high coverage—here coverage is 0%, so it must compensate, and it does. I'll set a 4.

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 adds a transition timeline to specific marker/region types, with a source+destination sound pair, matching FMOD's 'Add Transition Timeline' feature. It distinguishes this from a hard cut and names the animation targets (transition marker/region/loop region/magnet region), which helps separate it from sibling tools like marker_add_transition or marker_add_transition_region, even though those siblings likely do similar things.

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 description explicitly states when to use it (to add a crossfaded transition instead of a hard jump-cut, the professional technique for a seamless loop), and even notes limitations ('there's no scripted way to listen from here; audition in Studio'). It directly implies the alternative is a hard cut or using other transition tools, and instructs adjusting crossfade_length if the blend isn't right, which is practical usage guidance.

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