create_chord_progression

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

Goes well beyond the destructiveHint=true annotation by naming exactly what is destroyed (an existing clip in the target slot) and how to recover it (one undo_last). It also discloses concrete side effects the annotations cannot express: a 120 BPM .mid written to ~/Music/ableton-mcp/midi/ and operation with Live closed. It stops short of describing what is returned to the caller.

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-loads the core behavior plus an example, then moves through requirement, destination, and constraint in short clauses. Dense but every line carries information; the parenthetical undo note and the file-path detail are the only slightly crowded spots.

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 10-parameter destructive write tool with no output schema, the description covers prerequisites, both destination modes, the replacement/undo consequence, and format limits. The remaining gaps are secondary parameters (octave, sevenths, beats_per_chord) and the absence of any statement about what the call 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?

Schema description coverage is 0% across 10 parameters, so the description carries the full burden. It adds real meaning for degrees (degree-to-chord mapping with an example), root/scale (defaulting to the Set's scale, 7-note restriction) and the track+slot vs file_name destination split, but leaves octave, sevenths, beats_per_chord, and name unexplained.

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 concrete verb and resource ("Write held root-position chords built from scale degrees") and anchors it with a worked example: [1, 6, 4, 5] in C Major gives C Am F G. This clearly distinguishes it from sibling generators like create_midi_clip, write_notes, create_bassline, and create_drum_pattern.

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?

Explicitly names prerequisites and alternatives: requires a 7-note scale (excludes pentatonics and Minor Blues), root/scale fall back to the Set's scale via set_scale but must be given without Live, the track needs an instrument, and file_name is the path when Live is closed. It also states a hard exclusion ("Never creates tracks") and a meter limit ("4/4 only").

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