tracks_create

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

Annotations already declare the write/non-destructive/non-idempotent profile, and the description adds real behavioral detail beyond them: a track without an instrument is silent, plugins load asynchronously so their params appear in params.list 'a moment later', the new track is returned, and the operation is undoable. The async-loading warning is exactly the kind of gotcha an agent needs.

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-loads the core action in four words and every subsequent clause carries information (silence risk, plugin resolution, async loading, undo). The semicolon-chained sentences are dense and slightly run-on, costing it the top score.

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 only three parameters, full schema coverage, and no output schema, the description covers everything an agent needs: the two kinds, the instrument resolution path, the silent-track pitfall, async plugin timing, the return value, and reversibility.

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 the baseline is 3, but the description adds meaning the schema lacks: why instrument matters (silence without it), what a plugin URI actually is ('its uri = path, or its name'), and the default name behavior. It doesn't restate the enum values or note that instrument is ignored for audio beyond the schema's own '(MIDI only)'.

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?

Opens with a specific verb and resource ('Add a track at the end'), then immediately splits the resource into its two kinds ('midi' vs 'audio'). This is clearly distinguishable from siblings like tracks_update, tracks_duplicate, and tracks_set_instrument.

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?

Gives concrete routing guidance for the required parameter ('pass an instrument from instruments.list: a builtin URI or an installed plugin') and explains the consequence of omitting it. It doesn't name alternative tools (e.g. tracks_set_instrument for later changes) or when-not-to-use conditions, so it falls short of a 5.

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