run_live_menu

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

Annotations already flag destructiveHint=true and readOnlyHint=false, so the safety profile is covered. The description adds genuinely useful behavior beyond that: commands act on whatever is currently selected in Live, track_index changes selection first, and the agent is told to verify the result afterwards. It does not state error behavior for invalid/disabled menu items or whether labels are case-sensitive, which keeps it from a 5.

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?

Front-loaded with the core action, then examples, then the two behavioral caveats. The example list is long but earns its place by demonstrating label format. Only mild waste in the trailing 'check the result afterwards' phrasing.

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?

An output schema exists, so return values need not be described. For a deliberately open-ended tool that exposes an entire menu surface, the description covers the main behaviors but omits failure modes (invalid label, disabled command, wrong context) and guidance on when the specialized sibling tools are preferable.

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%, so the description carries the full burden. It explains track_index ('selects that track first') and illustrates the item label with many examples, which is meaningful. But it never specifies label matching rules (exact string, case sensitivity, submenu paths) or what happens on an ambiguous or missing label, leaving a gap on the primary required parameter.

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: run any command from Live's menu bar by its label, with a concrete example list ("Save Live Set", "Freeze Tracks", "Consolidate", etc.). It is distinguishable as a generic escape hatch, but it does not differentiate itself from siblings that already do some of these things (group_tracks, freeze_track, save_live_set, press_live_shortcut), which is a real ambiguity.

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 context is implied: you can invoke any menu command, track_index pre-selects a track, and selection-dependent commands act on the current selection. However, there is no explicit when-to-use-this vs use-the-dedicated-tool guidance, and no statement about what happens with an unknown or disabled menu label — both of which an agent needs before choosing this over group_tracks or freeze_track.

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