mark_music_moment

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

Annotations already declare readOnlyHint=false and destructiveHint=false, so the mutating-but-safe profile is structured data. The description adds that the mark is recorded for later training, which hints at persistence, but it doesn't say whether marks are retrievable later, what happens outside music mode, or whether repeats accumulate. Adequate, not rich.

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?

Two short sentences, front-loaded with the core action, with no filler. 'For training' is the one slightly wasted clause since it's never explained.

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 an output schema present, return values needn't be explained, and only two parameters exist. However, for a stateful tool tied to music mode, the description omits the key precondition (music mode active) and any note on how marks are later consumed, leaving a real gap.

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 50%: the 'kind' parameter already enumerates breakdown/lift/vocal/build/drop/other, so the description adds nothing there. The undocumented 'note' parameter is only indirectly illustrated by 'the chords just lifted'. That example is helpful but not a substitute for describing what the note field is for.

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 states a specific verb (flag/mark) and a specific object (a moment in the music mode recording), which clearly distinguishes it from siblings like start_music_mode and stop_music_mode. The parenthetical example ('the chords just lifted') makes the resource concrete. Minor vagueness remains in 'for training' – it doesn't say what the marks train or feed.

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?

'Call it the moment the user says so' gives a trigger condition, but it's implied rather than explicit: there's no statement that music mode must already be active, no handling when it isn't, and no alternative tool named. An agent can infer usage but must guess at prerequisites.

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