item

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

No annotations are provided, so the description carries the full disclosure burden. It does valuable work by clarifying non-obvious units (fades in seconds, positions/lengths in beats) and the host-path requirement for import, but it says nothing about what update mutates, whether changes persist/are undoable, or what list returns.

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?

Dense and front-loaded: the resource and action set come first, followed by unit clarifications and the import constraint. The telegraphic style wastes no words, though the sentence fragments make it slightly harder to parse than a fully formed brief.

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 13-parameter, multi-action tool with no annotations and no output schema, the description never says which parameters apply to which action (does list require track_index? does update require item_index?), leaving the agent to guess at the action/parameter matrix. It also omits any description of what list returns.

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?

With 0% schema coverage across 13 parameters, the description explains the most confusing ones: fade_in/fade_out units, position/length in beats, path, and as_new_track. However, mute, loop, gain_db, track_index, item_index, and start_beats are undocumented, and the distinction between start_beats and position_beats is left ambiguous.

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 names the resource (media items on a track) and enumerates the three supported operations (list | update | import), so an agent can tell this apart from siblings like track, midi, or fx. It lacks an explicit 'this is not X' comparison, but the scope is unambiguous.

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 is only implied through the action enum; there is no statement of when to choose item vs track or midi, nor prerequisites such as needing an existing track before importing. It does give one useful conditional hint (as_new_track=true makes new tracks) and a constraint for import (path must already exist on the REAPER host).

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