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

Annotations already declare readOnlyHint=true and destructiveHint=false, so 'Changes nothing' is largely redundant, but the description adds real behavioral context: a hard 16-bar ceiling, a payload-size caveat with a remedy, and the fact that the return includes the saved revision and musical context. That return-content detail matters because no output schema exists.

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?

Four short sentences, front-loaded with capability and format choices, then use case, then safety, then the size caveat. Every sentence carries signal except 'Changes nothing', which restates the readOnlyHint annotation.

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 4-parameter read tool with annotations covering safety and no output schema, the description supplies the essentials: scope limit, format choice, returned context, and size handling. Only minor gaps remain, such as the multi-part requirement, which the schema already states.

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 the enum values, the measure-range syntax, and the part_id conditionality are already documented. The description corroborates the format tradeoff and the bar limit but adds no syntax or defaults beyond the schema, so the 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 opens with a specific verb and resource ('Read up to 16 bars of an owned score') and names both output representations (compact ABC, editable MusicXML) plus accompanying data (saved revision, musical context). It is clearly distinct from write_bars and get_score, though it never explicitly names a sibling to contrast against.

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?

'Use for a bounded notation repair' gives a concrete triggering scenario rather than a generic 'use this to read', and 'Request fewer bars if the result is too large' provides a fallback when the call would fail. It stops short of naming exclusions or alternatives such as read_notation_view or get_score for non-repair reads.

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