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

With no annotations, the description carries the full burden and does well: it discloses the execution model ('dispatches to our AI workers (Modal)'), variable credits, file deletion after processing, auditability (mioffice.ai/account/tasks), and the absence of per-workspace subscriptions. This provides substantial context beyond the bare existence of the tool, though it omits failure modes or latency.

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 description is front-loaded with the core purpose but then becomes verbose with business/pricing details that could be summarized or placed elsewhere. It includes filler like 'Powered by MiOffice Song Engine' and a typo ('Engine..'). Each sentence does not earn its place; for a 0-parameter tool, this is over-specified.

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 no output schema and no annotations, the description covers the essential lifecycle: input (hum, lyrics), output (full song with vocals), cost model, data deletion, and audit trail. It doesn't explain the return format, but for a generation tool with zero formal parameters, it is sufficiently complete for an agent to understand what invoking this tool entails.

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?

The schema has 0 parameters, so baseline is 4. The description adds conceptual input semantics: 'Hum a melody, write lyrics' and 'your melody's key and tempo', which helps users understand what would be expected even though no formal parameters are declared. This exceeds the empty schema without adding specific syntax.

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+resource: 'Hum a melody, write lyrics, get a full song with vocals in your melody's key and tempo.' This clearly states the tool's function and distinguishes it from siblings like mio_ai_melody_to_music (likely instrumental) and mio_ai_song_generator (no hum input).

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?

The description provides operational constraints: 'AI Studio run', 'Day Pass and welcome credits do not include AI Studio', and file deletion. However, it does not explicitly state when to use this tool versus alternatives like mio_ai_melody_to_music or mio_ai_song_generator. Usage is implied but not directly contrasted with siblings.

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