create_clip

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

Annotations already declare readOnlyHint=false, destructiveHint=false and openWorldHint=false, so the safety profile is covered. The description adds only that the clip is MIDI and that user_prompt is for telemetry; it is silent on the important mutation behaviors an agent would want — what happens if the target slot already holds a clip, whether the clip is created empty, and whether a MIDI track is required.

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 one-sentence purpose followed by a compact parameter list; nothing extraneous. Minor waste in restating parameter names as their own definitions ('track_index: The index of the track...'), but the list is short and scannable.

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 needn't be explained, and the parameter semantics are covered. What's missing for a creation tool with 4 params is preconditions and failure behavior (slot occupancy, MIDI-track requirement) and whether the new clip is empty, which leaves an agent guessing at edge cases.

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 parameter block in the description carries real weight: it gives units for length ('beats', default 4.0), clarifies that clip_index refers to a clip slot rather than a clip, and explains that user_prompt is telemetry-only. The track_index/clip_index sentences mostly restate their names, but overall this compensates well for the empty schema.

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 ('Create a new MIDI clip') plus where it lands ('specified track and clip slot'), which cleanly separates it from create_audio_clip and create_arrangement_clip by the 'MIDI' + 'clip slot' language. It doesn't explicitly name those siblings, so differentiation is inferable rather than stated.

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?

There is no when-to-use or when-not-to-use guidance at all — no mention of Session vs Arrangement view, no note that the target track must be a MIDI track, and no pointers to add_notes_to_clip for populating the clip afterward. The purpose implies usage, but nothing actively guides selection against the many recording/creation siblings.

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