nudge_midi_notes

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

With no annotations, the description carries the full burden, and it does disclose real behavior: start/end move together (lengths preserved), edge notes clamp to item bounds, and an `out_of_bounds` vs `clamped` distinction is reported. However it omits the scope of the mutation — that only a filtered subset of notes (by channel, pitch range, beat range) is affected — and says nothing about reversibility/undo for a write operation.

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 operation, then the behavioral caveat, then a clean Args block; no filler sentences. The Args block containing only one of ten parameters is a structural oddity, but the prose itself is tight and well ordered.

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 mutation tool with no annotations, no output schema, and 0% schema description coverage, the description is too thin: it explains the shift and clamping but never explains note selection (which notes get nudged) or the `return_notes` toggle, and it references `out_of_bounds`/`clamped` return fields that no output schema defines.

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 must compensate and largely does not. `amount_beats` is explained well (units, sign, 0.25 = a 16th, -1.0 = a beat, 0 = no-op), but the nine filtering/selection parameters (track_index, item_index, channel, pitch_low/high, start_beat, end_beat, fields, return_notes) are never mentioned.

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+resource ('Shift MIDI notes in time by a number of beats') with a clear sign convention, and the length-preserving/clamping semantics implicitly separate it from quantize, stretch, or humanize. It never names an alternative sibling, so differentiation is left to inference 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?

Usage is implied by the operation itself (relative time shift), and the clamping note hints at the edge case of notes near item boundaries. There is no explicit when-to-use, when-not-to-use, or comparison against quantize_midi_notes/stretch_midi_notes, which all touch note timing.

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