delete_notes

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

Annotations already declare destructiveHint=true, readOnlyHint=false, and non-idempotency, so the safety profile is covered. The description meaningfully adds the half-open interval semantics ('notes starting in [start, end)'), the AND-combination of filters, and the required-filter constraint, which an agent needs to avoid over-deletion. It stops short of describing return/error behavior or idempotency quirks.

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 sentences, front-loaded with the core action and its filter selectors, then the constraint. Dense and largely waste-free, though the mapping of the various selectors is packed into one long clause that borders on a run-on.

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 mutation tool with no schema descriptions and no output schema, the clip-targeting parameters (track, slot, arrangement_clip) and the error/return behavior are left unexplained. What is present is accurate, but the definition does not fully equip an agent to call it on the correct clip.

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?

With 0% schema description coverage the description must carry the full burden, and it does document the deletion-defining params (note_ids, pitches, pitch_min/max, start/end) plus the half-open start/end semantics. But it never mentions three clip-targeting parameters — the required 'track', 'slot', and 'arrangement_clip' — leaving the agent to guess which clip is operated on.

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 ('Delete notes from a MIDI clip') and enumerates the selection mechanisms (note_ids, pitches, pitch range, time range, all=True), which clearly distinguishes it from the sibling delete_clip. It does not explicitly name the sibling it relates to (get_notes/write_notes/delete_clip), so it earns a 4 rather than a 5.

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?

Provides the key operating constraint ('Filters combine; at least one is required'), which is genuine usage guidance for invocation. However, it offers no guidance on when to prefer this over sibling tools like edit_notes or delete_clip, nor any prerequisites beyond the filter requirement.

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