add_midi_notes

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

With no annotations provided, the description carries the full burden of behavioral disclosure. It explains that track_pos_idx 'may become invalid if items are deleted/reordered,' discloses the default relative_start behavior, and warns about extending notes beyond item bounds. It doesn't mention error handling or reversibility, but the key behavioral traits are covered for a mutation tool.

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?

The description is well-organized with bold sections, bullet points, and a concrete example. It is longer than strictly necessary, but the structure makes it easy to scan. Every major section earns its place, though the Args list could have been more succinctly mapped to the actual parameter names.

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?

The tool has an output schema (not shown), so return values don't need explanation. The description covers item identification, parameter formats, and critical constraints (item length). It lacks details about atomicity, partial failure behavior, or how the track_index relates to item extraction, but for a MIDI editing tool, the description is quite complete.

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?

The description compensates for 0% schema coverage with extensive parameter details, including note fields (pitch, start_time, length_measure, etc.) and an example. However, there is a significant naming mismatch: the schema declares a parameter named 'item,' but the description's Args section refers to 'track_pos_idx' as the parameter name. This could confuse the agent about which schema field to populate. Additionally, relative_start is only mentioned as a per-note override, not clearly as a top-level parameter.

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?

The description begins with a specific verb and resource: 'Add multiple MIDI notes to a MIDI item in one operation.' It clearly distinguishes itself from the sibling tool add_midi_note (singular) by emphasizing 'multiple' and 'one operation.' This provides unambiguous purpose and scope.

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?

The description gives explicit usage guidance, including an important prerequisite warning about checking MIDI item bounds before adding notes. It also details two item identification methods and recommends when to use each: 'Use track_pos_idx for quick scripts, direct_item_id for reliability.' This is clear when-to-use guidance with alternatives.

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