check_voice_leading

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

With no annotations at all, the description carries the full behavioral burden and does most of it well: it discloses precisely which violations get reported and documents defaults such as voices ordered by average pitch and the 'voice holding a chord counts by its top note' rule. What it omits is what the check returns (issue list? per-bar report?) and whether it makes any change to the score.

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 what is checked, then parameter semantics, in one dense paragraph with no filler sentences. The chords explanation is crammed mid-sentence and slightly harder to parse than the leading rule list, but nothing is wasted.

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 analysis tool with no annotations and no output schema, the description covers the analysis domain thoroughly but leaves real holes: bar-range parameters, the 'flow' argument, and the shape of the returned diagnostics are all undocumented. An agent could call it, but would be guessing about both the range scope and what comes back.

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 0% across 7 parameters, so the description must compensate and only partly does. It adds real meaning for 'voices' (ordering and default), 'chords' (syntax, example, and which extra checks it enables), 'key' (required for leading-tone checks, with 'D'/'Bm' example), and 'max_leap' (the leap threshold in semitones), while 'flow', 'from_bar', and 'to_bar' are never explained.

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?

Names a specific verb and resource ('voice-leading check of the score') and then enumerates the exact rule categories checked: parallel/contrary fifths, octaves, unisons, hidden fifths in outer voices, crossings, spacing, and leaps. That is well beyond the sibling add_*/delete_* tools, which are all mutation helpers, so an agent can tell immediately this is an analysis tool.

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?

Usage is implied rather than stated: the tool is for harmonic/contrapuntal inspection, and the description explains the conditional value of the optional 'chords' argument (it 'adds' doubled thirds, missing thirds, non-chord tones, and requires 'key'). But there is no explicit when-to-use/when-not statement, and nothing says whether a score must be open or selected before calling.

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