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

Annotations already declare readOnly/idempotent/non-destructive, and the description adds cost-relevant reassurance ('Nothing is recognised again, no pages are charged') plus result semantics (nearest first, key, empty means no shift fits). That is genuine context beyond the annotations, though it omits any note on limits or performance.

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 core operation is front-loaded, but the opening is a long run-on sentence and the parentheticals ('a singer's voice, an instrument's compass, a kalimba's tines') are decorative rather than informative, diluting clarity.

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?

Given an output schema and full annotations, the description only needs to supply intent, cost behavior and follow-up routing, all of which are present. The only gap is the absence of explicit when-not guidance.

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 coverage is 100%, so low/high/part/file are already documented. The description adds only the part-scope default ('the whole score') and the semitones handoff, which is marginal extra meaning over the schema.

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 names the specific operation: determining whether a part's notes lie within a low…high range and enumerating the transpositions that fit. It also ties the result to transpose_score, which separates it from that sibling, though the phrasing is roundabout.

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?

It states the default scope ('default: the whole score') and gives a clear next step ('Pass a shift's semitones to transpose_score'), but never says when to use this versus transpose_score or describe_score, nor any prerequisites or exclusions.

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