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

Annotations already declare readOnly, idempotent and non-destructive, so the safety profile is covered. The description adds genuinely useful behavioral detail beyond that: one track per part, optional single-part export, transposition, and the non-obvious rule that repeats are played only once.

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?

A single compact sentence covering output format, optionality and the repeats rule, with the key facts front-loaded. Slightly noun-phrase phrasing ('A link to...') but no wasted sentences.

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?

With six well-documented parameters and an output schema, the description needn't explain return values, and it covers the salient behaviors (track layout, transposition, repeat handling). Only the relationship to sibling export tools is left unstated.

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 100%, so every parameter (key, part, semitones, save_to, file, recognition_id) is already documented in the schema. The description only alludes to part and transposition, adding no syntax or format detail beyond what the schema provides; baseline 3 applies.

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 states a specific resource and output form: the score as a MIDI file, one track per part, with optional single-part and transposed variants. It is clear what the tool produces, though it never explicitly distinguishes itself from siblings like export_score or get_download_link.

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?

'to listen to or rehearse with' implies a use case (playback/practice rather than notation editing), but there is no explicit when-to-use or when-not-to-use guidance relative to siblings such as export_score or transpose_score, leaving the agent to infer selection.

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