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

Annotations declare a safe read-only, idempotent operation, and the description adds substantive context beyond that: the 12,000-character input ceiling, accepted chord formats, the return payload (key change, chord mapping, widget sheet, Latin-only Courier PDF), and a reliability caveat that key estimates fail on key-changing songs.

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?

Front-loaded with the use case, then constraints, then returns, then exclusions and the failure caveat — no filler sentences, and each clause carries a distinct constraint an agent would otherwise have to discover by trial.

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 7-parameter transform tool with a full schema and an output schema, the description covers the remaining gaps: input size, accepted notation styles, mutually exclusive transposition modes, unsupported inputs, and the known accuracy limitation. An agent can invoke it correctly without guessing.

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 a baseline of 3 applies; the description earns a bump by stating the mutual-exclusivity rule across semitones / from_key+to_key / capo_fret and restating the numeric ranges. It still leans on the schema for spelling behavior and title formatting.

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 ('transpose chords or change the key of a song') plus explicit scope boundaries — chord names only, no audio, tablature or staff notation. It does not name or contrast with the siblings find_capo_options and show_chord_sheet, so the differentiation is left to inference.

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 this when you want to transpose chords or change the key of a song' gives a clear trigger condition, and the description spells out the three mutually exclusive transposition routes (semitones, from_key+to_key, capo_fret). It stops short of routing the agent to find_capo_options when only capo shapes are wanted, so it lacks explicit alternatives.

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