live_changes

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

No annotations exist, so the description carries the full burden, and it discloses significant traits: changes are net (moved-and-back counts as no change), authors are not reported, and reset re-baselines 'from now'. It stops short of explicitly saying the call is read-only relative to the song or that it maintains hidden per-song snapshot state that can be reset.

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?

Core behavior is front-loaded in the first clause, followed by the enumeration and then the two important caveats (net changes, first call is a look). The long category list is informative but dense and could have been grouped more tightly.

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?

There is no output schema, so the description must convey what comes back, and the enumeration of change categories does that adequately. The shape of the returned diff (grouping, field names) is never described, which leaves a gap for an agent that needs to parse results.

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?

Only one optional parameter and the schema already documents it at 100% coverage, so the baseline is high; the description adds a nuance beyond the schema by clarifying that reset means re-baselining from the current moment rather than clearing history.

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 resource and operation: a diff of the currently open song since the previous call, with an explicit enumeration of tracked categories (tracks, events, mixer, tempo/loop, markers/arranger). This is unmistakably different from snapshot-style siblings like live_song or live_track_state.

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?

Gives real usage context: the first call for a song is a baseline look and reports nothing, so an agent knows not to interpret an empty first result as an error. It does not name alternatives (e.g., song_diff, song_history) or state when to prefer those over this.

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